© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99155
    Prev
    Next
    INDEX
    Explanations

    common code prefixes

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

    This neuron responds to underscores within code identifiers, i.e. it detects snake_case names.

    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
    positionen
    -1.57
     dát
    -1.53
     siè
    -1.52
     ſu
    -1.51
     remercier
    -1.41
    翃
    -1.40
    cadilly
    -1.39
    <>());
    -1.38
     defekt
    -1.38
    ïs
    -1.38
    POSITIVE LOGITS
     for
    2.05
     other
    1.95
     new
    1.89
     as
    1.84
     after
    1.78
     one
    1.74
     not
    1.66
     still
    1.63
     of
    1.63
     this
    1.62
    Activations Density 0.032%

    No Known Activations