© 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. 19211
    Prev
    Next
    INDEX
    Explanations

    encoding="utf-8" or "utf-8"="

    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
    elte
    0.87
     ahí
    0.84
    क्टर
    0.81
     omkring
    0.79
    ş
    0.79
     いう
    0.79
     मुताबिक
    0.77
     شہری
    0.75
     facendo
    0.74
    zeti
    0.74
    POSITIVE LOGITS
    Wis
    0.81
    ب
    0.75
     والص
    0.74
    Recommendation
    0.74
     Hölder
    0.73
     накло
    0.72
    柜
    0.71
     Recommendation
    0.71
    openConnection
    0.71
     Ou
    0.71
    Activations Density 0.000%

    No Known Activations