© 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. 129330
    Prev
    Next
    INDEX
    Explanations

    commercial photography and agency models

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

    states and historical figures

    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
    總
    0.50
    vors
    0.49
    紥
    0.45
    зом
    0.45
    бовать
    0.44
     суммы
    0.44
    fections
    0.43
    Editors
    0.42
    ద్ధ
    0.42
     बांटा
    0.42
    POSITIVE LOGITS
    moon
    0.48
     seer
    0.46
    گیر
    0.46
     Hid
    0.46
     ヒ
    0.44
     tani
    0.44
     Alh
    0.44
     Gian
    0.43
     hiver
    0.43
    면에
    0.43
    Activations Density 0.001%

    No Known Activations