Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1467
    Prev
    Next
    INDEX
    Explanations

    rounded shapes and curves

    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_29_width_65k_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
     Passwort
    0.79
     literacy
    0.71
     خير
    0.70
    Millis
    0.70
     transaksi
    0.69
     metadata
    0.69
     மாநில
    0.68
    赃
    0.68
    Metadata
    0.67
    贓
    0.67
    POSITIVE LOGITS
     curved
    2.25
     shape
    2.19
     shapes
    2.09
     rounded
    2.09
     curves
    2.08
     shaped
    2.00
     curve
    1.98
     circular
    1.95
     Shape
    1.93
     oval
    1.90
    Activations Density 1.003%

    No Known Activations