© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39048
    Prev
    Next
    INDEX
    Explanations

    heavy equipment components

    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
    耷
    -1.63
    источник
    -1.55
     简介
    -1.49
    潁
    -1.48
    Ⓥ
    -1.48
    诋
    -1.47
     černé
    -1.45
    伤感
    -1.44
     escolares
    -1.41
     Quais
    -1.41
    POSITIVE LOGITS
     often
    1.69
     of
    1.66
     such
    1.54
    \\
    1.52
     if
    1.40
     dann
    1.40
    大多
    1.39
     also
    1.35
     so
    1.35
     /
    1.30
    Activations Density 0.195%

    No Known Activations