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. 41201
    Prev
    Next
    INDEX
    Explanations

    leading civil rights concepts

    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
     बरसा
    0.85
     Alltag
    0.80
    bibnamefont
    0.77
    洖
    0.77
     বরা
    0.76
     Lesser
    0.76
     személy
    0.75
    ywidual
    0.75
    ceğine
    0.74
    ясплат
    0.73
    POSITIVE LOGITS
     black
    0.92
     Black
    0.85
    black
    0.84
    Black
    0.79
    黑
    0.79
     blacks
    0.78
     into
    0.74
     BLACK
    0.69
     by
    0.65
     ब्लैक
    0.64
    Activations Density 0.012%

    No Known Activations