© 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. 231569
    Prev
    Next
    INDEX
    Explanations

    secondhand shopping

    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
    فی
    0.70
    in
    0.62
    래
    0.57
    ONE
    0.55
    ع
    0.53
    Player
    0.52
    VARIABLE
    0.52
    ف
    0.52
    In
    0.51
    1
    0.51
    POSITIVE LOGITS
     kön
    0.46
    lässlich
    0.43
     св
    0.42
     какое
    0.42
     الشيطان
    0.42
    鈳
    0.41
     يكن
    0.41
     يتع
    0.40
    ğmen
    0.40
     있어요
    0.40
    Activations Density 0.001%

    No Known Activations