© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by names

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

    . T

    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
     బ్రిటి
    0.52
    ❻
    0.49
    preliquidacion
    0.47
     estrogens
    0.46
    LetterLocation
    0.46
    ナソニック
    0.46
     bebés
    0.46
    ❽
    0.46
     ALEXANDER
    0.45
     Hbdm
    0.45
    POSITIVE LOGITS
     he
    0.61
     Mr
    0.52
    he
    0.52
    ice
    0.52
    mathrm
    0.50
    ini
    0.50
    org
    0.50
    ies
    0.49
      
    0.48
    ia
    0.48
    Activations Density 0.378%

    No Known Activations