© 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. 154355
    Prev
    Next
    INDEX
    Explanations

    admit or claim

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

    search keywords and file types

    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
     *
    0.55
     Illustration
    0.54
     ☆
    0.51
     イラスト
    0.49
     シ
    0.49
     Vad
    0.48
    Y
    0.48
     Issues
    0.46
     Globalization
    0.46
    LLA
    0.46
    POSITIVE LOGITS
    服
    0.47
     defens
    0.47
     නැ
    0.47
     essencial
    0.46
     ehrlich
    0.46
     openly
    0.45
     depres
    0.45
    поле
    0.45
    实在
    0.45
     admit
    0.44
    Activations Density 0.000%

    No Known Activations