© 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. 103302
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts

    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
    蓠
    -2.14
    裃
    -1.81
    犼
    -1.77
     ſte
    -1.77
     utilisées
    -1.77
     !!!!
    -1.76
     extrêmement
    -1.73
    慢慢的
    -1.72
     unſ
    -1.70
    ౧
    -1.70
    POSITIVE LOGITS
     with
    2.92
     in
    2.67
     while
    2.42
     by
    2.27
     only
    2.14
     all
    2.11
     as
    2.08
     on
    2.05
     within
    2.03
     at
    1.94
    Activations Density 0.049%

    No Known Activations