© 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. 34270
    Prev
    Next
    INDEX
    Explanations

    role or description

    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
    is
    0.68
    ع
    0.66
    구성
    0.59
     seguire
    0.57
    يلا
    0.57
    iędzy
    0.57
     variedad
    0.55
    uine
    0.55
    ע
    0.54
    Buenos
    0.54
    POSITIVE LOGITS
     salaried
    0.54
    :
    0.54
     who
    0.53
     proff
    0.53
     quarterbacks
    0.52
     commentator
    0.50
     mosquitoes
    0.50
     maximizes
    0.50
    一名
    0.50
     polarization
    0.49
    Activations Density 0.144%

    No Known Activations