© 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. 102132
    Prev
    Next
    INDEX
    Explanations

    sterling silver and winners

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

    silver trophies and prize

    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
    शाह
    0.43
     ভূত
    0.43
    坌
    0.42
     Fakultas
    0.42
    jha
    0.42
    bě
    0.41
     Anzeige
    0.41
    部屋
    0.40
     ケ
    0.40
     भाषा
    0.39
    POSITIVE LOGITS
     silverware
    0.66
     winners
    0.61
     silver
    0.57
    银
    0.55
     Winners
    0.54
     победи
    0.53
     Silver
    0.52
     trophies
    0.52
    Silver
    0.52
     victories
    0.51
    Activations Density 0.061%

    No Known Activations