© 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. 124084
    Prev
    Next
    INDEX
    Explanations

    French Edition, GT cars

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

    double-slit experiment

    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
    了一些
    0.46
     ಕ
    0.45
     externalities
    0.43
    quiry
    0.43
     मेल
    0.43
    برای
    0.43
    لين
    0.42
    ᱹ
    0.42
    Shoes
    0.42
     حب
    0.42
    POSITIVE LOGITS
    de
    0.46
     Zentrum
    0.46
     interactions
    0.46
     modern
    0.45
    overline
    0.44
    แด
    0.44
     Memoirs
    0.44
     Jahrhund
    0.44
     healing
    0.43
     existent
    0.43
    Activations Density 0.000%

    No Known Activations