© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1419
    Prev
    Next
    INDEX
    Explanations

    open followed by terms

    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_17_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
     যাহ
    0.79
    嶙
    0.77
    esley
    0.75
    ▟
    0.74
     mania
    0.74
    महारा
    0.73
     ktorí
    0.72
     lavage
    0.72
    opis
    0.71
    pering
    0.71
    POSITIVE LOGITS
     doors
    1.12
    ended
    1.07
     ended
    0.96
     closed
    0.91
     Doors
    0.91
    Ended
    0.88
    Closed
    0.86
    ="("
    0.85
     kimono
    0.85
    weathermap
    0.85
    Activations Density 0.280%

    No Known Activations