© 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. 1459
    Prev
    Next
    INDEX
    Explanations

    webpages or financial options

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

    sexual health and dating resources

    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
     "\
    0.52
     درخت
    0.50
    
    0.49
    ٤
    0.49
    爫
    0.46
     Vật
    0.46
     deel
    0.45
     toho
    0.45
     Schröder
    0.45
    <tbody>
    0.45
    POSITIVE LOGITS
     UNITED
    0.78
     rehearse
    0.73
     epidermis
    0.73
     parece
    0.71
     desplaz
    0.70
     xmas
    0.70
     solamente
    0.70
     elizabeth
    0.70
     citas
    0.68
     webpages
    0.66
    Activations Density 0.053%

    No Known Activations