© 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. 78864
    Prev
    Next
    INDEX
    Explanations

    health, anatomy, activity, expression

    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
    鐙
    0.48
     liquidation
    0.47
    is
    0.46
    on
    0.46
    ancia
    0.44
    as
    0.42
     valuation
    0.41
    u
    0.41
     promotion
    0.41
    placement
    0.41
    POSITIVE LOGITS
     azal
    0.58
     spekt
    0.54
     künstler
    0.52
     lensa
    0.52
     ruang
    0.49
     judul
    0.48
     berubah
    0.48
     şark
    0.47
     bunyi
    0.47
     bisher
    0.46
    Activations Density 0.014%

    No Known Activations