© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    styles and materials

    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
    amanam
    0.52
     беремен
    0.50
     breastfeeding
    0.48
     hyperparameters
    0.48
     rollerskates
    0.48
    👙
    0.47
    underwear
    0.47
    🤱
    0.47
     inext
    0.46
     reelection
    0.46
    POSITIVE LOGITS
     Contemporary
    0.77
     contemporary
    0.68
     Modern
    0.66
     Moderne
    0.63
     faux
    0.62
     Collection
    0.62
     Collections
    0.60
     Coastal
    0.59
     distressed
    0.58
    Modern
    0.56
    Activations Density 0.011%

    No Known Activations