© 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. 67531
    Prev
    Next
    INDEX
    Explanations

    special characters and names

    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
    -1.93
     a
    -1.90
     for
    -1.90
     an
    -1.86
     To
    -1.78
     after
    -1.77
     problems
    -1.73
     seems
    -1.70
     $
    -1.69
     Remember
    -1.69
    POSITIVE LOGITS
     ワゴン
    2.11
    艄
    1.88
    ⅏
    1.87
    踯
    1.86
    臯
    1.84
     pierwsze
    1.80
    ჻
    1.80
     praticamente
    1.79
    歘
    1.76
    蹀
    1.76
    Activations Density 0.003%

    No Known Activations