© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 18886
    Prev
    Next
    INDEX
    Explanations

    classifying people based on traits

    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
     grasa
    0.97
    MVP
    0.82
     रावत
    0.79
    애
    0.76
    LIN
    0.76
     bandages
    0.76
     ಔಷ
    0.75
     Poultry
    0.73
    MOR
    0.72
     ')[
    0.72
    POSITIVE LOGITS
     pouring
    0.82
     फ्रेम
    0.75
     zem
    0.74
     Tou
    0.71
     दुस
    0.69
     sø
    0.68
     Aryan
    0.67
    邗
    0.67
     vork
    0.67
    මාණය
    0.66
    Activations Density 0.001%

    No Known Activations