© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7441
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects uppercase alphanumeric identifiers and acronyms (e.g. legal docket numbers, model/version codes, and other all-caps labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    occurrences of the letter “D,” especially when it appears as a standalone capital in acronyms or as a trailing “d” in short letter clusters.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the letter 'D' appearing in technical contexts, particularly in code, legal citations, and acronyms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     staunch
    -1.84
    ICOLON
    -1.75
     There
    -1.74
     办
    -1.73
     尔
    -1.68
    redited
    -1.61
     cautious
    -1.60
    asanjo
    -1.59
     nifty
    -1.59
     slight
    -1.58
    POSITIVE LOGITS
    (),
    1.82
    ’
    1.81
     tillegg
    1.78
    rée
    1.73
     poches
    1.71
    copied
    1.69
    },
    1.66
    hline
    1.66
    '\
    1.65
     anglais
    1.64
    Activations Density 0.090%

    No Known Activations