© 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. 36343
    Prev
    Next
    INDEX
    Explanations

    code and database identifiers

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

    The neuron fires on standalone numeric tokens (e.g. array indices or literal numbers).

    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
    isip
    -0.94
    schen
    -0.94
     maquin
    -0.91
    itee
    -0.90
     transposition
    -0.90
    Teknik
    -0.90
     waifu
    -0.89
    ordum
    -0.89
     教程
    -0.88
     桌面
    -0.88
    POSITIVE LOGITS
     Cbd
    1.00
     dieser
    0.87
    }{*}{
    0.84
     who
    0.84
     meilleurs
    0.82
    而非
    0.82
     that
    0.82
    GetSize
    0.82
     Strecken
    0.79
     creadores
    0.79
    Activations Density 0.004%

    No Known Activations