© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29757
    Prev
    Next
    INDEX
    Explanations

    document figures 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-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ज़िंदगी
    0.43
     साझेदारी
    0.41
    сант
    0.41
     узна
    0.40
     spy
    0.40
     appren
    0.40
    逍
    0.40
     reconnaissance
    0.39
     तित
    0.39
    website
    0.39
    POSITIVE LOGITS
     Figure
    1.48
    Figure
    1.47
     Figures
    1.36
     diagrams
    1.31
    Figures
    1.27
    図
    1.24
     graphs
    1.22
     Tables
    1.22
     Figs
    1.21
     Diagrams
    1.21
    Activations Density 0.011%

    No Known Activations