© 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. 106983
    Prev
    Next
    INDEX
    Explanations

    Sale Discount

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

    upcoming freedom

    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
    B
    0.55
    Q
    0.53
    b
    0.50
    m
    0.49
    Б
    0.46
     atteints
    0.45
    芯
    0.45
    契
    0.44
     Ни
    0.44
    spor
    0.44
    POSITIVE LOGITS
     vuccanti
    0.49
     querying
    0.48
     sitting
    0.48
    ;
    0.47
     commenting
    0.46
     queries
    0.46
    পিত
    0.46
    ūra
    0.45
    ças
    0.45
     belonging
    0.45
    Activations Density 0.001%

    No Known Activations