© 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. 146796
    Prev
    Next
    INDEX
    Explanations

    line for, nearby while, array format, enhance your

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

    Docker containers and images

    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
     ഭക്ഷ
    0.51
     ब्यूटी
    0.47
    tiktok
    0.47
     kolor
    0.46
     rodz
    0.46
    ids
    0.46
     probl
    0.46
     bambini
    0.46
    🧸
    0.46
     খাবারের
    0.44
    POSITIVE LOGITS
    лении
    0.52
    iliary
    0.47
    Var
    0.46
    ходе
    0.45
    ப்படுத்த
    0.44
    ла
    0.43
     непре
    0.43
     externalities
    0.43
     तकनी
    0.43
    很有
    0.42
    Activations Density 0.000%

    No Known Activations