© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136692
    Prev
    Next
    INDEX
    Explanations

    see growth, work hard, dates, ability to decide

    np_acts-logits-general · gemini-2.5-flash-lite

    asking if something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polytechn
    0.47
     Vitamins
    0.45
    ZIE
    0.45
    "]))
    0.44
    
    0.44
     Selatan
    0.44
     ప్రకట
    0.44
     प्रोत्साहित
    0.44
    Eth
    0.43
     presentamos
    0.43
    POSITIVE LOGITS
     ווא
    0.50
     mario
    0.47
     Кай
    0.46
    숴
    0.46
     adhered
    0.46
     fickle
    0.45
    찜
    0.45
     isim
    0.45
     נו
    0.45
     arada
    0.45
    Activations Density 0.001%

    No Known Activations