© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6580
    Prev
    Next
    INDEX
    Explanations

    far more, far beyond

    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_22_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
    癀
    0.78
    좀
    0.78
     좀
    0.76
    arap
    0.75
     조금
    0.75
     पासवर्ड
    0.75
     دوباره
    0.75
     少し
    0.73
    堇
    0.72
    elt
    0.72
    POSITIVE LOGITS
    reaching
    1.20
     reaches
    1.19
     reaching
    1.18
     reached
    1.03
     reach
    1.02
     removed
    1.00
    fetched
    0.97
    removed
    0.96
     Reach
    0.93
     exceeded
    0.91
    Activations Density 0.023%

    No Known Activations