© 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. 7551
    Prev
    Next
    INDEX
    Explanations

    khanacademy.org

    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
     ধর
    0.94
    ATIVE
    0.90
     connues
    0.90
    tragung
    0.90
    <unused45>
    0.90
     पक्षा
    0.86
     составе
    0.86
    HideFlags
    0.85
    rements
    0.85
     तलैया
    0.85
    POSITIVE LOGITS
     کت
    0.73
     Printed
    0.72
    COUN
    0.70
     균
    0.68
     Heat
    0.68
    heat
    0.67
     Sets
    0.65
     Fehl
    0.65
    crim
    0.65
     प्रिंट
    0.64
    Activations Density 0.001%

    No Known Activations