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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2356
    Prev
    Next
    INDEX
    Explanations

    supplying advanced capabilities

    np_acts-logits-general · gemini-2.5-flash-lite

    for racial justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̬
    0.66
    ̙
    0.64
    ͍
    0.64
     белән
    0.62
     pacc
    0.59
    <0x9F>
    0.59
    ̻
    0.59
    ̜
    0.58
    ͖
    0.58
    llllllll
    0.57
    POSITIVE LOGITS
     subtleties
    0.93
     conceivable
    0.88
     profoundly
    0.85
     straightforward
    0.83
     extravagance
    0.83
     twofold
    0.83
    Notwithstanding
    0.83
     unmistakable
    0.82
     frameworks
    0.79
     Notwithstanding
    0.79
    Activations Density 0.434%

    No Known Activations