© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 712
    Prev
    Next
    INDEX
    Explanations

    company and platform names

    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
     または
    1.06
     અથવા
    0.98
     یا
    0.96
     किंवा
    0.96
    تی
    0.96
    áty
    0.95
     세
    0.91
     이런
    0.91
    と
    0.90
     또는
    0.90
    POSITIVE LOGITS
    ®
    0.72
     Chart
    0.59
    Food
    0.58
    لفة
    0.57
     Lego
    0.57
    MIC
    0.57
    Chart
    0.57
     Food
    0.56
     Российской
    0.56
     представление
    0.56
    Activations Density 1.455%

    No Known Activations