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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2484
    Prev
    Next
    INDEX
    Explanations

    acronyms in parentheses

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

    The neuron is keyed to numeric tokens—i.e. sequences of digits such as version numbers, years, or other numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    sour
    -0.82
    seille
    -0.81
    sri
    -0.79
    SCP
    -0.79
    shy
    -0.77
    sling
    -0.77
    slate
    -0.76
    sci
    -0.76
    sara
    -0.76
    smb
    -0.75
    POSITIVE LOGITS
    XS
    1.77
     HTS
    1.75
     ZS
    1.72
     TCS
    1.66
    LS
    1.66
    QS
    1.64
     LBS
    1.64
     IFS
    1.63
     PDS
    1.63
    FS
    1.61
    Activations Density 0.306%

    No Known Activations