© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1221
    Prev
    Next
    INDEX
    Explanations

    python code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    <0x00>
    0.94
    ുന്നു
    0.86
    Ꮖ
    0.84
    ๚
    0.83
    此外
    0.83
    国务院
    0.82
    .*/
    0.81
    ("");
    0.81
     कुर्सी
    0.80
    뷁
    0.77
    POSITIVE LOGITS
    aries
    0.94
    acol
    0.93
    seits
    0.92
     Adrián
    0.90
    ático
    0.89
     kilomètres
    0.89
    icle
    0.88
    ript
    0.88
    ᴇ
    0.88
    LAND
    0.88
    Activations Density 0.101%

    No Known Activations