© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49201
    Prev
    Next
    INDEX
    Explanations

    decide

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    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
     불러
    0.37
     tou
    0.37
    helm
    0.36
    oye
    0.35
     spacious
    0.34
    অ
    0.34
    ጫ
    0.34
    psies
    0.34
    WebApplication
    0.34
    犹
    0.33
    POSITIVE LOGITS
     decided
    2.94
     decide
    1.98
     решила
    1.96
     decidió
    1.95
     решил
    1.95
     decides
    1.91
     decidido
    1.91
     решили
    1.91
     décidé
    1.89
     decidiu
    1.83
    Activations Density 0.065%

    No Known Activations