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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10077
    Prev
    Next
    INDEX
    Explanations

    Same-Origin Policy

    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_24_width_16k_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
     penser
    0.77
     dolore
    0.71
    >
    0.70
    import
    0.69
    ze
    0.68
    essayer
    0.68
    零
    0.68
    
    0.68
     arrière
    0.67
    최
    0.67
    POSITIVE LOGITS
     Conservation
    0.78
    បង្ហ
    0.78
     Shivaji
    0.74
     Certification
    0.73
     कोटा
    0.72
     Conflicts
    0.72
     onFailure
    0.71
     Exceptions
    0.71
     Supplies
    0.70
     Rojo
    0.70
    Activations Density 0.003%

    No Known Activations