© 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. 58653
    Prev
    Next
    INDEX
    Explanations

    chapter and number

    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
    轵
    -1.88
     patienter
    -1.75
     食物
    -1.59
     permettent
    -1.53
     våra
    -1.51
     อาหาร
    -1.50
     varje
    -1.49
    めんなさい
    -1.48
     Vitamina
    -1.45
     tiré
    -1.45
    POSITIVE LOGITS
     who
    1.99
     why
    1.70
     with
    1.63
    hline
    1.55
     their
    1.55
     how
    1.54
     others
    1.47
     her
    1.43
     then
    1.43
     zuerst
    1.38
    Activations Density 0.003%

    No Known Activations