© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    useless followed by description

    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
    e
    -3.36
    d
    -3.22
    蛧
    -2.91
    ляции
    -2.67
    𓐍
    -2.58
    焌
    -2.52
    section
    -2.50
    f
    -2.47
    hilangan
    -2.42
    鸰
    -2.42
    POSITIVE LOGITS
    ly
    2.75
    {
    2.64
    cloudf
    2.28
    "
    2.28
    where
    2.28
    which
    2.23
    
    2.17
     \
    2.11
    還沒
    2.11
     Anyway
    2.09
    Activations Density 0.001%

    No Known Activations