© 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. 11845
    Prev
    Next
    INDEX
    Explanations

    plot line styles and labels

    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
     डीडी
    0.44
    TextImage
    0.42
    戦闘
    0.42
    🧼
    0.41
    суз
    0.39
    скус
    0.39
    プール
    0.39
     વપરા
    0.38
    睢
    0.38
    郋
    0.38
    POSITIVE LOGITS
     linestyle
    0.99
     linewidth
    0.98
    linewidth
    0.86
    linestyle
    0.86
    LineWidth
    0.84
     lw
    0.74
     label
    0.73
     line
    0.73
     linha
    0.72
     Line
    0.71
    Activations Density 0.009%

    No Known Activations