© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2431
    Prev
    Next
    INDEX
    Explanations

    Notable achievements, features, and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ing
    2.09
    ри
    2.00
    ian
    1.91
    ő
    1.88
    ية
    1.87
    رو
    1.85
    о
    1.85
    il
    1.84
    ㅎㅎ
    1.80
    
    1.80
    POSITIVE LOGITS
    s
    2.67
    ्स
    1.88
    ের
    1.79
    sphere
    1.71
    ség
    1.63
    ים
    1.61
    телно
    1.59
    ों
    1.58
     vrsta
    1.58
     superficially
    1.58
    Activations Density 0.010%

    No Known Activations