© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27422
    Prev
    Next
    INDEX
    Explanations

    craft beer and craftsmanship

    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
    人才
    0.39
    𝘵
    0.39
     FF
    0.37
     artwork
    0.37
     stumbling
    0.36
     Revue
    0.36
     Cru
    0.35
     frying
    0.35
    テ
    0.35
    ள்
    0.35
    POSITIVE LOGITS
    smanship
    0.74
    speople
    0.72
     beer
    0.61
     beers
    0.58
    ビール
    0.57
     Beers
    0.57
     artisan
    0.55
    manship
    0.55
     Beer
    0.54
    Beer
    0.53
    Activations Density 0.003%

    No Known Activations