© 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. 31-GEMMASCOPE-2-RES-262K
    7. 136574
    Prev
    Next
    INDEX
    Explanations

    javascript event binding

    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_31_width_262k_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
    ੀ
    0.50
    οι
    0.47
    BoolVar
    0.42
    زی
    0.41
    눔
    0.41
    кова
    0.41
     вули
    0.41
    ク
    0.41
    움
    0.41
    블
    0.40
    POSITIVE LOGITS
     faculties
    0.48
     profund
    0.47
     deductive
    0.47
    厭
    0.46
    ក្នុងការ
    0.44
     hand
    0.43
     altitudes
    0.43
     tedious
    0.43
     latitudes
    0.43
    ដៃ
    0.43
    Activations Density 0.003%

    No Known Activations