© 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. 66738
    Prev
    Next
    INDEX
    Explanations

    Seller may

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

    academic discussion topics

    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
     дорого
    0.50
     көзге
    0.46
    Œ
    0.46
    dropPanel
    0.45
     랜
    0.45
    धानिक
    0.45
     налази
    0.45
    FlaskApp
    0.45
    DispatchRequest
    0.45
     bap
    0.45
    POSITIVE LOGITS
     Attitudes
    0.54
     intellectuals
    0.49
     Attitude
    0.49
     industries
    0.49
     উ
    0.48
     Boundaries
    0.48
     Ihrer
    0.47
     Enemies
    0.47
     attitude
    0.47
     die
    0.46
    Activations Density 0.001%

    No Known Activations