© 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. 8092
    Prev
    Next
    INDEX
    Explanations

    eight

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

    eight

    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
    <unused15>
    0.39
    <unused5>
    0.38
     ১৯৪৭
    0.34
    isComposite
    0.34
     ২০১৭
    0.34
    <unused55>
    0.33
    OSED
    0.33
    <unused37>
    0.33
    ﻒ
    0.33
    <unused36>
    0.33
    POSITIVE LOGITS
     Eight
    2.88
    八
    2.83
     eight
    2.81
     вось
    2.73
     八
    2.66
     आठ
    2.63
    Eight
    2.56
    ８
    2.56
    eight
    2.53
     oito
    2.50
    Activations Density 0.489%

    No Known Activations