© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5659
    Prev
    Next
    INDEX
    Explanations

    response `=` assignment

    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_17_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
    s
    1.28
    ы
    0.81
    नु
    0.80
    ো
    0.80
    مو
    0.79
     toán
    0.73
    d
    0.72
    m
    0.72
     οποίο
    0.71
     absoluta
    0.71
    POSITIVE LOGITS
     Fl
    1.05
    Fl
    1.04
    Ս
    0.98
    filler
    0.96
    <i>
    0.93
     LEVEL
    0.91
     Sent
    0.90
    Level
    0.89
    FAKE
    0.89
    Olympic
    0.89
    Activations Density 0.074%

    No Known Activations