© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7285
    Prev
    Next
    INDEX
    Explanations

    uncertainty and difficult situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     書き
    1.03
     erotic
    1.02
    infected
    1.01
     imaginative
    0.99
    ికె
    0.99
    酩
    0.99
    ርግ
    0.97
    寳
    0.97
     antibacterial
    0.95
    <unused1928>
    0.95
    POSITIVE LOGITS
    0.77
    ush
    0.74
    we
    0.73
    l
    0.72
     Main
    0.71
    ous
    0.71
    s
    0.71
    on
    0.70
    ami
    0.70
    as
    0.70
    Activations Density 0.000%

    No Known Activations