© 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-262K
    7. 48891
    Prev
    Next
    INDEX
    Explanations

    peppers

    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_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
    .
    0.95
    ي
    0.91
    i
    0.84
    an
    0.74
    ק
    0.73
    in
    0.73
     in
    0.68
     according
    0.64
    u
    0.63
    י
    0.62
    POSITIVE LOGITS
    اوز
    0.68
    avacak
    0.63
    roon
    0.54
     compter
    0.53
    聝
    0.53
     गतिविधि
    0.52
    嚥
    0.52
    ردن
    0.52
     герой
    0.52
     Gaspar
    0.52
    Activations Density 0.001%

    No Known Activations