© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41145
    Prev
    Next
    INDEX
    Explanations

    mounted, based, shock, nec, wide, induced, binding, transmit, access, reported

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

    hyphenated technical terms in patent or scientific document text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     with
    -2.81
     both
    -2.03
     only
    -1.86
     one
    -1.72
     was
    -1.72
     but
    -1.71
     several
    -1.69
    ↵
    -1.68
     through
    -1.66
     without
    -1.66
    POSITIVE LOGITS
    ⚋
    1.71
    횃
    1.70
    nige
    1.69
    ztes
    1.68
     Giochi
    1.67
    izamos
    1.66
    chende
    1.63
    YOUR
    1.62
    ݯ
    1.56
    푉
    1.56
    Activations Density 0.150%

    No Known Activations