© 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. 191462
    Prev
    Next
    INDEX
    Explanations

    batch processing and core themes

    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
    슝
    0.44
    زيز
    0.42
    里昂
    0.42
    
    0.42
    absorption
    0.41
    fragment
    0.41
    Couldn
    0.41
    Logging
    0.40
     Леон
    0.40
    Serialized
    0.40
    POSITIVE LOGITS
     Colors
    0.42
     employer
    0.42
     arbets
    0.42
     lich
    0.42
     arbeids
    0.42
     ä
    0.41
    imum
    0.41
     farmer
    0.41
     Economics
    0.40
     Finance
    0.40
    Activations Density 0.003%

    No Known Activations