© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59526
    Prev
    Next
    INDEX
    Explanations

    static Function

    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
     baada
    -1.09
     diesen
    -1.09
     habari
    -1.05
     aceites
    -1.04
     Warszaw
    -1.04
     same
    -1.04
    ’
    -1.01
    來
    -0.99
     impos
    -0.99
     maisha
    -0.98
    POSITIVE LOGITS
    むしろ
    1.09
     използ
    0.99
    　＊
    0.95
    中略
    0.94
     діяльності
    0.94
    although
    0.94
    　↓
    0.93
    0.91
    おかげ
    0.90
    劝
    0.88
    Activations Density 0.017%
    No Known Activations