© 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. 2283
    Prev
    Next
    INDEX
    Explanations

    privacy and domain names

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

    privacy and model identity

    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
     cale
    0.38
     گی
    0.37
    妖
    0.36
    ี่ป
    0.36
    зен
    0.36
     তরঙ্গ
    0.36
    HandleTypeDef
    0.36
    ูป
    0.35
    ಾಗಿದೆ
    0.35
     І
    0.34
    POSITIVE LOGITS
     privacy
    0.87
    privacy
    0.86
     Privacy
    0.84
    Privacy
    0.81
    隐私
    0.71
     privacidad
    0.70
     privacidade
    0.67
     Datensch
    0.57
    web
    0.55
     copyright
    0.54
    Activations Density 0.025%

    No Known Activations