© 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. 236514
    Prev
    Next
    INDEX
    Explanations

    services rendered

    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
     sockets
    0.56
     puertos
    0.51
    념
    0.50
    세대
    0.49
     gallons
    0.49
     carreteras
    0.48
     mirrored
    0.47
    восто
    0.47
     nitrates
    0.47
     مواقع
    0.47
    POSITIVE LOGITS
    a
    0.59
    such
    0.58
     Pr
    0.50
    an
    0.50
    f
    0.49
    lar
    0.47
    Dennis
    0.47
    hips
    0.46
    pture
    0.46
    dies
    0.46
    Activations Density 0.000%

    No Known Activations