© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1977
    Prev
    Next
    INDEX
    Explanations

    the case, therefore read, valuable insights

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

    Unicode graphical characters

    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
     
    0.23
    ↵
    0.19
    commands
    0.18
    get
    0.18
    est
    0.17
    find
    0.17
     ‘
    0.17
     “
    0.17
    current
    0.17
    ing
    0.16
    POSITIVE LOGITS
    য়ং
    0.21
    Eppo
    0.19
    ীয়তে
    0.19
    <unused2150>
    0.19
    ార్క్
    0.19
    اداسی
    0.18
    Pinterest
    0.18
    মিনা
    0.18
    
    0.18
    <unused2042>
    0.18
    Activations Density 0.038%

    No Known Activations