© 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. 76625
    Prev
    Next
    INDEX
    Explanations

    questions followed by no

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

    asking questions

    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
    彝
    0.50
    只是
    0.46
    ForgotPassword
    0.42
    리와
    0.41
    分別
    0.41
    分别
    0.41
    ндар
    0.41
    联合国
    0.40
    스와
    0.39
    母亲
    0.39
    POSITIVE LOGITS
    ?
    0.58
     ----------
    0.54
     Whether
    0.50
    ville
    0.50
     whether
    0.50
     -
    0.47
    ?-
    0.46
     Genau
    0.45
    ？
    0.45
     Yep
    0.44
    Activations Density 0.043%

    No Known Activations