© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    prices and quantities

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

    ranges and approximations

    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
    ５
    0.44
     ২
    0.38
    ２
    0.38
    ６
    0.37
    ４
    0.36
    １
    0.35
     ۲
    0.34
     ۵
    0.34
    ٥
    0.34
     ५
    0.34
    POSITIVE LOGITS
     વધી
    0.41
     lowest
    0.40
     pegged
    0.37
     above
    0.36
     estimated
    0.35
     unchanged
    0.35
     wynosi
    0.35
     highest
    0.34
    above
    0.34
     recorded
    0.33
    Activations Density 0.133%

    No Known Activations