© 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. 117423
    Prev
    Next
    INDEX
    Explanations

    username, password, login, forgotten

    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
     hyaluronic
    -0.93
    šče
    -0.84
    场景
    -0.82
    拯
    -0.80
    faden
    -0.77
     carboxylic
    -0.77
    будь
    -0.76
    wußt
    -0.75
     prostřed
    -0.75
    宜蘭
    -0.73
    POSITIVE LOGITS
    crossover
    0.85
    lanca
    0.82
     Speaker
    0.77
     зеле
    0.77
     Cities
    0.76
     another
    0.76
    jeli
    0.76
    OrderItem
    0.75
    Jedi
    0.74
     Reading
    0.73
    Activations Density 0.004%

    No Known Activations