© 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. 784
    Prev
    Next
    INDEX
    Explanations

    elements, flashlight, list, adapter, advanced, problems, synthetic

    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
    อังกฤษ
    0.46
    дру
    0.44
     euismod
    0.42
     CLIENT
    0.41
    wohner
    0.41
    얼
    0.40
    ineed
    0.40
    엉
    0.39
     uname
    0.39
    űkö
    0.39
    POSITIVE LOGITS
     Weeks
    0.45
     Chou
    0.45
    Wa
    0.41
     Libr
    0.41
     Expressions
    0.41
     Nights
    0.40
    وا
    0.40
     Victor
    0.40
     herv
    0.40
     Cape
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.