© 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. 10-GEMMASCOPE-RES-131K
    7. 102372
    Prev
    Next
    INDEX
    Explanations

    assigned tokens, code comments, titles

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

    function or variable definitions in source code, particularly at the point where parameters or assignments are being declared.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on tokens that serve as structural or “header” markers in code and documentation—long runs of punctuation (dashes, asterisks), comment‐oriented symbols (//, /*), underscores in identifiers, and other section‐separator or header‐style tokens.

    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
     this
    -1.91
     работают
    -1.84
     récord
    -1.73
     нынеш
    -1.71
     живут
    -1.70
     lâmpada
    -1.67
     zwi
    -1.65
    
    -1.60
     paño
    -1.59
    ívne
    -1.55
    POSITIVE LOGITS
    on
    1.55
    in
    1.52
     in
    1.51
     is
    1.49
     meeste
    1.47
    le
    1.41
     cedera
    1.40
    i
    1.38
     or
    1.37
    ne
    1.35
    Activations Density 0.002%

    No Known Activations