© 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. 216540
    Prev
    Next
    INDEX
    Explanations

    numbers and list items

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

    impacts how on the formal

    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
     mies
    0.50
     aval
    0.47
     руками
    0.46
    厮
    0.44
     niemals
    0.44
     sze
    0.43
     roues
    0.43
     correr
    0.43
    amaan
    0.43
     pouze
    0.41
    POSITIVE LOGITS
    ро
    0.49
    ங்கா
    0.47
    :
    0.47
     трево
    0.45
     infix
    0.45
    ியின்
    0.44
    रूप
    0.44
     Osama
    0.44
     trató
    0.44
    感じる
    0.44
    Activations Density 0.000%

    No Known Activations