© 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. 34-GEMMASCOPE-RES-131K
    7. 47585
    Prev
    Next
    INDEX
    Explanations

    entity followed by its definition

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

    The neuron activates on programming identifiers—names of variables, functions, classes, and similar tokens in source code.

    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
    matisch
    -1.07
    boucles
    -0.96
    Vlast
    -0.96
    chaussures
    -0.92
    ᥆
    -0.92
    Funny
    -0.91
    occu
    -0.91
     Joke
    -0.91
    chaussure
    -0.90
    capulco
    -0.90
    POSITIVE LOGITS
     data
    1.13
     candidates
    1.05
    localctx
    1.04
    Info
    0.97
     still
    0.97
    info
    0.96
     info
    0.93
    ,
    0.92
     possibly
    0.91
     might
    0.91
    Activations Density 0.035%

    No Known Activations