© 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. 7652
    Prev
    Next
    INDEX
    Explanations

    brand names or people

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

    special characters, numbers, and single letters

    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
    0.55
     N
    0.49
     M
    0.48
    .
    0.47
     G
    0.47
     D
    0.45
     E
    0.45
     S
    0.44
     A
    0.44
     V
    0.44
    POSITIVE LOGITS
    蠵
    0.55
     Elektrokhimiya
    0.50
    gdock
    0.46
    狨
    0.46
    mataspid
    0.44
     चिकित्स
    0.43
     صہیون
    0.43
    逈
    0.43
    Strafpunkte
    0.42
    캿
    0.42
    Activations Density 0.112%

    No Known Activations