© 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. 10-GEMMASCOPE-RES-131K
    7. 8524
    Prev
    Next
    INDEX
    Explanations

    member 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_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
    ↵↵↵
    -1.72
     by
    -1.52
     to
    -1.49
     in
    -1.32
     even
    -1.30
     you
    -1.24
     faktisk
    -1.21
     endorsed
    -1.20
    ntilde
    -1.20
     actually
    -1.20
    POSITIVE LOGITS
     or
    1.49
    얘
    1.46
     dlaczego
    1.43
    üğü
    1.39
     których
    1.28
     cosméticos
    1.27
    например
    1.27
     quelconque
    1.27
    或者
    1.24
     verschieden
    1.23
    Activations Density 0.104%

    No Known Activations