© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136786
    Prev
    Next
    INDEX
    Explanations

    foreign-sounding suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vibes
    0.43
    大
    0.41
    बै
    0.40
    ংক
    0.40
     Fiberglass
    0.40
     Comrade
    0.40
     throughout
    0.39
    ฆ
    0.39
    Painting
    0.39
     IRC
    0.38
    POSITIVE LOGITS
     tịch
    0.44
    ionado
    0.44
    URNIZOR
    0.42
     ordenada
    0.42
    leps
    0.40
    orna
    0.40
    ordnet
    0.39
     Ordn
    0.39
    seiten
    0.38
    ttino
    0.38
    Activations Density 0.001%

    No Known Activations