© 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. 14410
    Prev
    Next
    INDEX
    Explanations

    fearless, unarmed, unmanned

    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
    ing
    -2.66
     irgend
    -2.61
     suporta
    -2.45
     Which
    -2.38
    鬟
    -2.36
     这个
    -2.33
     Traducción
    -2.31
     MUCH
    -2.30
     superfí
    -2.30
    颪
    -2.25
    POSITIVE LOGITS
    \
    2.81
    F
    2.53
     expanse
    2.31
    沇
    2.28
    哔
    2.23
    で
    2.17
    𓋼
    2.17
    当我
    2.14
     необходи
    2.13
     extravagant
    2.09
    Activations Density 0.008%

    No Known Activations