© 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. 70301
    Prev
    Next
    INDEX
    Explanations

    dusting electronics or furniture

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

    glucose production in the liver

    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
     použ
    0.52
     arbitr
    0.51
    郓
    0.48
     nový
    0.48
    вия
    0.45
    舉
    0.45
     použív
    0.45
     Customize
    0.45
     zákon
    0.45
     autorità
    0.44
    POSITIVE LOGITS
    growth
    0.57
     ২০১০
    0.54
    reflex
    0.52
    ga
    0.50
    dif
    0.49
    g
    0.49
    lint
    0.49
    mes
    0.48
    le
    0.48
    ler
    0.47
    Activations Density 0.000%

    No Known Activations