© 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. 22-GEMMASCOPE-2-RES-262K
    7. 19327
    Prev
    Next
    INDEX
    Explanations

    the program script code function

    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_22_width_262k_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
     beinhaltet
    0.93
    ™.
    0.85
     consists
    0.82
    ไม่ได้
    0.81
     prevede
    0.80
    分钟
    0.79
     contém
    0.79
     führt
    0.79
     ?",
    0.78
    .`);
    0.78
    POSITIVE LOGITS
     жизнь
    0.92
     life
    0.86
     overall
    0.79
     easier
    0.79
     жизни
    0.78
     sure
    0.76
     життя
    0.75
     stronger
    0.74
     जीवन
    0.73
    burg
    0.73
    Activations Density 0.046%

    No Known Activations