© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    त्तों
    0.76
    áty
    0.72
    컸
    0.70
    சித்த
    0.70
    ält
    0.69
    ры
    0.69
    agama
    0.67
    喜
    0.66
    陷
    0.66
    баев
    0.65
    POSITIVE LOGITS
     Seafood
    1.04
     moi
    0.91
     transitory
    0.90
     vogue
    0.88
     Steak
    0.86
    立場
    0.86
     Semiconductor
    0.86
    ೃಷ್ಣ
    0.86
     plonge
    0.85
     jukebox
    0.85
    Activations Density 0.000%

    No Known Activations