© 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. 10-GEMMASCOPE-RES-131K
    7. 60393
    Prev
    Next
    INDEX
    Explanations

    result in consequences

    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_10/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
     will
    -2.08
     have
    -1.59
     didn
    -1.41
     various
    -1.39
     what
    -1.38
     came
    -1.38
     
    -1.28
     did
    -1.23
     not
    -1.20
     „
    -1.18
    POSITIVE LOGITS
    
    1.40
    だいたい
    1.30
     可愛
    1.29
     بايد
    1.28
    электро
    1.28
     状態
    1.27
     your
    1.20
     productie
    1.20
     voegen
    1.19
     物語
    1.19
    Activations Density 0.088%

    No Known Activations