© 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. 1368
    Prev
    Next
    INDEX
    Explanations

    bold markdown or pipe operator

    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
     CME
    0.76
     ಬೆ
    0.76
    Chlor
    0.71
    肥
    0.71
    thiaz
    0.71
    Beth
    0.69
    杭
    0.68
    鲍
    0.68
    芮
    0.68
    NaClO
    0.67
    POSITIVE LOGITS
     চট্টগ্রামের
    1.03
     Girl
    0.98
     girl
    0.90
     Roberts
    0.89
     চট্টগ্রামে
    0.89
     Padilla
    0.88
     cannabinoids
    0.86
     Hood
    0.86
     Hadid
    0.85
     guerr
    0.83
    Activations Density 1.119%

    No Known Activations