© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 377
    Prev
    Next
    INDEX
    Explanations

    details depend

    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
     que
    0.49
     occasione
    0.48
    *
    0.47
     visibly
    0.47
    v
    0.46
     curioso
    0.45
     entirely
    0.44
    [
    0.44
     ocasión
    0.43
     alegre
    0.43
    POSITIVE LOGITS
     optimization
    1.34
     분석
    1.33
     quantification
    1.31
     optimizations
    1.30
     전문가
    1.30
    Optimization
    1.29
     refinements
    1.29
     optimizing
    1.27
    优化
    1.25
     implementation
    1.25
    Activations Density 1.547%

    No Known Activations