© 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. 40960
    Prev
    Next
    INDEX
    Explanations

    language introduction snippets

    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
     gastronomía
    -2.27
     artesanía
    -1.89
     špec
    -1.88
     моего
    -1.84
     dát
    -1.81
     mía
    -1.80
     моей
    -1.80
     dvou
    -1.71
     všechny
    -1.70
     extraña
    -1.70
    POSITIVE LOGITS
     Although
    2.23
     although
    1.97
    虽说
    1.93
     Despite
    1.92
     Even
    1.91
     or
    1.89
    .
    1.88
     While
    1.82
     on
    1.82
     in
    1.73
    Activations Density 0.007%

    No Known Activations