© 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. 2305
    Prev
    Next
    INDEX
    Explanations

    good humour and paste

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

    paste and related words

    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
     Andrews
    0.44
     erythemat
    0.41
    equation
    0.40
    ithmetic
    0.39
     август
    0.39
    Andrews
    0.39
    ита
    0.38
    宙
    0.38
     Ariz
    0.38
     Epstein
    0.38
    POSITIVE LOGITS
     humour
    0.64
     humor
    0.64
     Humor
    0.63
     Paste
    0.56
     paste
    0.55
     Past
    0.55
     pasted
    0.54
    paste
    0.53
    Paste
    0.52
     humorous
    0.50
    Activations Density 0.002%

    No Known Activations