© 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. 164310
    Prev
    Next
    INDEX
    Explanations

    specific sequence markers

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

    how often things happen

    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
    DetailUI
    0.46
     ن
    0.46
    すなわち
    0.45
    ;
    0.45
     homot
    0.45
    ید
    0.44
    لاء
    0.43
     isothermal
    0.42
    mêmes
    0.42
    焊接
    0.42
    POSITIVE LOGITS
    positivo
    0.50
    ಇ
    0.47
    ktiv
    0.47
    comstock
    0.47
    tec
    0.46
    bahn
    0.45
    OP
    0.44
    Nt
    0.43
     けど
    0.43
    ٹنگ
    0.42
    Activations Density 0.000%

    No Known Activations