© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9834
    Prev
    Next
    INDEX
    Explanations

    parser and if statements

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

    The neuron fires on numeric literal tokens (numbers) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     quà
    -0.94
    İŞ
    -0.93
     другую
    -0.92
    شما
    -0.89
    ската
    -0.86
     secretos
    -0.85
    ❹
    -0.84
    æk
    -0.82
    jq
    -0.81
    lagte
    -0.81
    POSITIVE LOGITS
     if
    1.18
     nadat
    0.95
     приготовить
    0.93
     pieces
    0.93
    勒
    0.90
     If
    0.85
     any
    0.85
    piece
    0.82
     UTM
    0.82
     determine
    0.81
    Activations Density 0.006%

    No Known Activations