© 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. 150234
    Prev
    Next
    INDEX
    Explanations

    term started, incredible amounts

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

    Scottish Rite, MACD, carcinoma, click

    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
    \
    0.49
     laughing
    0.48
    大力
    0.48
     επιχει
    0.46
     ENGINEERS
    0.46
    '
    0.46
     gaussian
    0.45
     editors
    0.44
     inspecting
    0.44
    եր
    0.44
    POSITIVE LOGITS
    bah
    0.55
    serial
    0.55
    n
    0.52
    nimi
    0.52
    nej
    0.51
    interests
    0.51
    mest
    0.51
    canvas
    0.51
    salas
    0.49
    nj
    0.48
    Activations Density 0.000%

    No Known Activations