© 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. 22-GEMMASCOPE-RES-131K
    7. 64960
    Prev
    Next
    INDEX
    Explanations

    ferrofluidic screens

    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_22/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
     Dinas
    -1.00
    ͢
    -0.98
     プリント
    -0.96
    princip
    -0.95
    期望
    -0.95
     existem
    -0.94
    不存在
    -0.92
     年级
    -0.91
     آزمون
    -0.91
    だけではなく
    -0.90
    POSITIVE LOGITS
    Despite
    1.23
     by
    1.20
    Through
    1.13
    Meski
    1.10
    Being
    1.09
     at
    1.05
    uyor
    1.03
     showed
    1.02
     uses
    1.02
     through
    1.00
    Activations Density 0.001%

    No Known Activations