© 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. 182834
    Prev
    Next
    INDEX
    Explanations

    ranked bymalicious executablelots of

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

    cheapest, highest, tight

    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
     Citt
    0.47
    INK
    0.45
    theater
    0.42
    Pued
    0.41
    舫
    0.41
    ink
    0.41
    jš
    0.41
    তেও
    0.41
    ської
    0.40
    Caution
    0.40
    POSITIVE LOGITS
     увели
    0.48
     тура
    0.46
     折り
    0.45
     ไล
    0.45
     calculado
    0.45
     보고
    0.44
     赵
    0.44
     cálculo
    0.43
     افزایش
    0.43
     алуу
    0.43
    Activations Density 0.000%

    No Known Activations