© 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. 5387
    Prev
    Next
    INDEX
    Explanations

    referencing figures, tables, sections

    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
     improvis
    0.45
     medley
    0.42
    ĕç
    0.39
     edibles
    0.39
     brandy
    0.38
     bandana
    0.38
    ⴷ
    0.38
     pastime
    0.38
    ("|"+"
    0.38
    বৃ
    0.37
    POSITIVE LOGITS
     Figure
    0.98
    Figure
    0.96
     refer
    0.84
    Fig
    0.83
    ref
    0.82
     Fig
    0.81
     Table
    0.80
    Table
    0.79
    Section
    0.77
     references
    0.76
    Activations Density 0.007%

    No Known Activations