© 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. 219376
    Prev
    Next
    INDEX
    Explanations

    convention delegate

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

    Gb, quotes, electronics

    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
    CH
    0.54
     برنام
    0.50
    GEM
    0.49
    MEM
    0.48
    Dat
    0.48
    _
    0.48
    Gem
    0.48
    }}=
    0.47
    가
    0.46
    SIGN
    0.46
    POSITIVE LOGITS
     normalizing
    0.52
    鶘
    0.50
    ರವಾಗಿ
    0.49
    рила
    0.49
     normalization
    0.48
    列表中
    0.47
    酈
    0.46
    ंजे
    0.46
    ស្រាយ
    0.45
    fda
    0.45
    Activations Density 0.001%

    No Known Activations