© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12020
    Prev
    Next
    INDEX
    Explanations

    character creation and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iburg
    0.41
     almu
    0.41
    medal
    0.40
    %';
    0.40
    mineral
    0.39
     확인함
    0.39
    ";}
    0.39
    oplus
    0.39
     cholesterol
    0.39
    ^{-
    0.39
    POSITIVE LOGITS
     playable
    0.95
     character
    0.73
     캐릭터
    0.73
    playable
    0.72
    キャラクター
    0.72
     Character
    0.71
     characters
    0.70
     Characters
    0.68
     karakter
    0.68
     Charakter
    0.66
    Activations Density 0.259%

    No Known Activations