© 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. 44790
    Prev
    Next
    INDEX
    Explanations

    KC refused

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

    sharing actions and states

    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
    اث
    0.40
    ارة
    0.40
     Hadrian
    0.39
    Sonic
    0.37
     التالي
    0.37
    azität
    0.37
    뼈
    0.37
     появи
    0.36
     ${(
    0.35
    يران
    0.35
    POSITIVE LOGITS
     dalamnya
    0.51
    google
    0.48
    lovens
    0.47
     dosa
    0.46
    st
    0.43
     rans
    0.43
     chopped
    0.42
     ಭಾವ
    0.42
     lakes
    0.42
     feast
    0.42
    Activations Density 0.000%

    No Known Activations