© 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. 128407
    Prev
    Next
    INDEX
    Explanations

    Brazilian elections

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

    research, synthesis, and transformation

    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
    ೆಂಟ್
    0.52
     Zel
    0.47
     hujan
    0.46
    permal
    0.46
     गिलास
    0.46
    літы
    0.45
     burlap
    0.45
    禟
    0.45
     کوچ
    0.45
     вело
    0.44
    POSITIVE LOGITS
    is
    0.53
    in
    0.50
     ü
    0.47
    u
    0.46
    端
    0.46
     Cloning
    0.44
     পরিষে
    0.43
    от
    0.42
    驟
    0.42
     বিধ
    0.41
    Activations Density 0.000%

    No Known Activations