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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41336
    Prev
    Next
    INDEX
    Explanations

    web links ending in .com

    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
     Commod
    0.75
     함
    0.73
     commodity
    0.71
    commod
    0.70
    Commod
    0.69
     commod
    0.68
     Monsters
    0.66
    恝
    0.65
     Mono
    0.65
     commodities
    0.63
    POSITIVE LOGITS
     abajo
    0.79
    Education
    0.78
    Educational
    0.73
     تحقی
    0.72
     desviación
    0.71
     मेहनत
    0.70
     მან
    0.70
    education
    0.70
    educational
    0.69
     Dernière
    0.69
    Activations Density 0.002%

    No Known Activations