© 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. 7052
    Prev
    Next
    INDEX
    Explanations

    end bracket punctuation

    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
    Negative Logits
    -
    0.87
    Emotion
    0.80
    log
    0.78
    a
    0.77
    வும்
    0.74
     аппарат
    0.74
     Arrow
    0.74
     불구하고
    0.73
    ally
    0.72
    lar
    0.70
    POSITIVE LOGITS
     Pase
    1.13
    郅
    1.10
     postmodern
    1.03
    tiden
    0.99
     بينما
    0.99
     Entretanto
    0.95
     criterio
    0.93
     আমায়
    0.93
     प्रैक्टिस
    0.93
    ບໍລິ
    0.92
    Activations Density 0.000%

    No Known Activations