© 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. 237800
    Prev
    Next
    INDEX
    Explanations

    canyon, MBE, quick medical

    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
     Carpath
    0.53
     Lauf
    0.49
    Ꮺ
    0.48
     Boeh
    0.47
    وم
    0.47
    кой
    0.47
    からです
    0.47
    повід
    0.46
    плы
    0.46
     Tutto
    0.46
    POSITIVE LOGITS
    that
    0.54
    even
    0.53
    </b>
    0.47
    simulate
    0.46
    jin
    0.46
    than
    0.44
    ree
    0.43
    create
    0.43
    inness
    0.43
    min
    0.43
    Activations Density 0.001%

    No Known Activations