© 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. 22-GEMMASCOPE-RES-131K
    7. 128389
    Prev
    Next
    INDEX
    Explanations

    end of definition or phrase

    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_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
    thée
    -1.05
     Find
    -1.02
    يكية
    -0.98
    Find
    -0.94
    関連リンク
    -0.94
     reconocida
    -0.90
    PropertyChanged
    -0.90
    次回
    -0.88
    quetes
    -0.88
     unterstützt
    -0.88
    POSITIVE LOGITS
    şim
    1.15
     départ
    1.02
    ただし
    1.02
     tarifas
    1.00
     enfance
    0.99
    lI
    0.97
    😯
    0.93
    名字
    0.92
     produkter
    0.91
    区别
    0.91
    Activations Density 0.005%

    No Known Activations