© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136846
    Prev
    Next
    INDEX
    Explanations

    discover where

    np_acts-logits-general · gemini-2.5-flash-lite

    needs, requirements, faster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.47
    Line
    0.47
    x
    0.46
    \
    0.45
    ped
    0.44
     movilidad
    0.44
    pak
    0.43
     commander
    0.43
    l
    0.43
    er
    0.42
    POSITIVE LOGITS
    ZIE
    0.52
     ಡ
    0.52
     ஜூ
    0.52
    לא
    0.50
    埧
    0.47
     приблизи
    0.47
     זי
    0.47
     क्लोरीन
    0.47
     हसीना
    0.46
     ጠ
    0.44
    Activations Density 0.001%

    No Known Activations