© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2216
    Prev
    Next
    INDEX
    Explanations

    adding or introducing new things

    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_16_width_65k_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
    _
    0.87
    '
    0.73
    ק
    0.67
    ^
    0.65
    ח
    0.64
    ك
    0.63
     an
    0.63
    $
    0.61
     are
    0.61
    וב
    0.61
    POSITIVE LOGITS
    ar
    1.11
    i
    0.95
    in
    0.94
    as
    0.88
    t
    0.81
    ro
    0.80
    o
    0.77
    l
    0.75
    at
    0.74
    u
    0.73
    Activations Density 0.660%

    No Known Activations