© 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. 14079
    Prev
    Next
    INDEX
    Explanations

    integer declarations

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

    The neuron highly activates on short local variable names (like p, s, i, c, str) in code—i.e. it spots variable declarations and uses of those identifiers.

    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
    媗
    -1.54
    ,
    -1.44
     вашим
    -1.43
    łach
    -1.42
    ,<
    -1.41
    まずは
    -1.40
     [`
    -1.36
     maniera
    -1.33
    ,”
    -1.32
    palen
    -1.32
    POSITIVE LOGITS
     Their
    1.41
     that
    1.31
     on
    1.28
     seiner
    1.23
     préférable
    1.19
     ihren
    1.18
    他們的
    1.16
     available
    1.16
     experience
    1.15
     similar
    1.13
    Activations Density 0.016%

    No Known Activations