© 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. 245262
    Prev
    Next
    INDEX
    Explanations

    teeth whitening, loss, waves, artist

    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
     Gets
    0.47
     constellations
    0.46
     Calculates
    0.46
    RR
    0.46
    누
    0.45
    বরা
    0.44
    BTS
    0.44
    MBOLS
    0.44
     validates
    0.43
    XII
    0.43
    POSITIVE LOGITS
    icas
    0.49
    ítés
    0.46
    icarboxylic
    0.46
    aş
    0.46
     જેના
    0.46
    icillium
    0.46
    oxa
    0.45
    痧
    0.45
    публи
    0.44
    isar
    0.44
    Activations Density 0.000%

    No Known Activations