© 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. 98723
    Prev
    Next
    INDEX
    Explanations

    experience in survey

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

    phrase "penis" or "penises"

    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
    C
    0.55
    L
    0.55
    K
    0.55
    G
    0.54
     Company
    0.52
    D
    0.50
    J
    0.50
    class
    0.50
     G
    0.49
     Manufacturer
    0.49
    POSITIVE LOGITS
    HasStarred
    0.59
    orderDisplay
    0.55
    йын
    0.51
     いや
    0.50
    stepToken
    0.49
     పాల్గొన్నారు
    0.49
    ๅ
    0.49
    oksatta
    0.48
    routingHeader
    0.48
     имел
    0.48
    Activations Density 0.000%

    No Known Activations