© 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. 199780
    Prev
    Next
    INDEX
    Explanations

    wine rack, cringe, linked, playground

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

    usual conditions

    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
     Panch
    0.48
    рят
    0.47
    pcion
    0.47
    ς
    0.45
    лл
    0.45
     burial
    0.44
    ход
    0.44
    ል።
    0.43
    ﺔ
    0.43
    镜像
    0.43
    POSITIVE LOGITS
     vertebr
    0.47
    ègre
    0.47
     speci
    0.47
     portée
    0.46
    ミュージ
    0.44
     Tiere
    0.44
     जीवों
    0.44
    ència
    0.43
    éhez
    0.43
    나무
    0.43
    Activations Density 0.001%

    No Known Activations