© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221202
    Prev
    Next
    INDEX
    Explanations

    available in form transgress earth

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

    declarations and sections

    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
    Negative Logits
    枝
    0.49
     Mind
    0.47
    amélioration
    0.46
    wrapp
    0.46
    Trou
    0.45
    excellence
    0.45
    evaluation
    0.45
    C
    0.45
    ಪಾ
    0.44
    Gabri
    0.44
    POSITIVE LOGITS
     tự
    0.54
    يمة
    0.48
     chatId
    0.47
     juta
    0.47
     chon
    0.46
     alat
    0.46
     miatt
    0.46
     kazi
    0.46
     सेकंड
    0.46
     ал
    0.45
    Activations Density 0.000%

    No Known Activations