© 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. 66517
    Prev
    Next
    INDEX
    Explanations

    ISBNs and editions

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

    code and technical phrases

    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
     расти
    0.55
    stays
    0.51
    ཋ
    0.50
    rbrakk
    0.50
     aisément
    0.49
     voert
    0.49
    妷
    0.48
     половины
    0.48
    vég
    0.47
     نصف
    0.47
    POSITIVE LOGITS
     \
    0.59
     relish
    0.54
    在
    0.53
    Y
    0.53
    řez
    0.50
     frequency
    0.48
     waterfront
    0.47
     repellent
    0.47
     UFC
    0.47
    ও
    0.47
    Activations Density 0.000%

    No Known Activations