© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6837
    Prev
    Next
    INDEX
    Explanations

    Drayton Manor

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

    LaTeX environments for matrices and tables

    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
    ="$(
    0.40
     oryg
    0.39
    вига
    0.38
     Salute
    0.38
     vér
    0.38
    ISTR
    0.37
    .$(
    0.37
     Kensington
    0.36
     $\{(
    0.36
     NEM
    0.36
    POSITIVE LOGITS
    bosch
    0.42
     נוס
    0.41
    natives
    0.41
    ボ
    0.41
    یکشن
    0.39
     الوحد
    0.39
     yo
    0.38
    徂
    0.38
     pribadi
    0.37
    γμα
    0.37
    Activations Density 0.000%

    No Known Activations