© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42770
    Prev
    Next
    INDEX
    Explanations

    tips or advice to follow

    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
     because
    -2.11
     it
    -2.08
     each
    -1.91
     by
    -1.82
     with
    -1.82
     during
    -1.71
     However
    -1.68
     every
    -1.66
     the
    -1.66
     Certainly
    -1.66
    POSITIVE LOGITS
    ?”
    1.73
     españoles
    1.73
     llamados
    1.70
    ⚢
    1.63
    ")]
    1.62
    ㋛
    1.60
     mencionados
    1.57
     dépenses
    1.55
     contenidos
    1.54
    ╽
    1.53
    Activations Density 0.045%

    No Known Activations