© 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. 144325
    Prev
    Next
    INDEX
    Explanations

    más importantes

    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
    and
    1.51
    to
    1.27
    as
    1.17
    i
    1.17
    ض
    1.10
    *
    1.05
    e
    1.04
    ב
    1.02
     powied
    1.01
    :
    0.92
    POSITIVE LOGITS
     tortured
    0.85
     consecrated
    0.83
    olated
    0.82
    yección
    0.77
    ರವ
    0.75
     objectionable
    0.75
    不但
    0.74
    უნქ
    0.74
     thatched
    0.73
    ስቃ
    0.73
    Activations Density 0.009%

    No Known Activations