© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110931
    Prev
    Next
    INDEX
    Explanations

    "give" or "Graduation" + numbers/tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ênes
    -0.82
    谊
    -0.71
     training
    -0.71
     America
    -0.71
    年間
    -0.70
    стка
    -0.68
     glu
    -0.67
    imagined
    -0.66
     Nordrhein
    -0.66
    ramine
    -0.66
    POSITIVE LOGITS
    Bands
    0.94
     implementation
    0.93
     Bands
    0.85
     Parame
    0.85
     arrears
    0.84
     implemented
    0.83
     hike
    0.80
     IBA
    0.80
    TokenNameRPAREN
    0.78
     オープン
    0.76
    Activations Density 0.012%

    No Known Activations