© 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. 206568
    Prev
    Next
    INDEX
    Explanations

    options to subscribe: monthly, yearly

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

    different strengths

    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
     괴
    0.51
     궁
    0.48
    蕌
    0.47
     คณิต
    0.47
     ذریع
    0.46
     endere
    0.45
    愺
    0.45
     permitido
    0.45
    スタンダ
    0.45
    bracht
    0.44
    POSITIVE LOGITS
    лды
    0.53
     $\
    0.52
     optimizations
    0.51
     DETAILS
    0.50
     getUser
    0.49
    ="${
    0.49
    lax
    0.48
    עם
    0.48
    ("\
    0.48
    yu
    0.46
    Activations Density 0.000%

    No Known Activations