© 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. 40623
    Prev
    Next
    INDEX
    Explanations

    makes it easy

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

    upcoming regulations or potential solutions

    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
     jak
    0.55
    ↵
    0.52
     I
    0.51
     as
    0.51
    :
    0.46
     a
    0.45
     lok
    0.44
     tient
    0.44
     tho
    0.44
    let
    0.43
    POSITIVE LOGITS
    ঙ্কের
    0.58
    ၀၀
    0.56
     শাহ
    0.55
     அழிக்க
    0.54
    <unused83>
    0.54
    amélioration
    0.54
    グレ
    0.53
     দক্ষতার
    0.53
     অনিবার
    0.53
     அழி
    0.52
    Activations Density 0.000%

    No Known Activations