© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2689
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and annotations

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

    latex commands

    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
     basilaires
    0.31
    這位
    0.28
     CLIENTI
    0.28
     estacion
    0.28
     REGIUNI
    0.28
    鵠
    0.28
     quieras
    0.28
    乆
    0.27
    穢
    0.27
    罷
    0.27
    POSITIVE LOGITS
    hyperref
    0.40
    citet
    0.34
    usepackage
    0.34
    xspace
    0.33
    url
    0.33
     url
    0.33
    %\
    0.32
    TODO
    0.32
     \
    0.31
    options
    0.31
    Activations Density 0.000%

    No Known Activations