© 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-65K
    7. 61577
    Prev
    Next
    INDEX
    Explanations

    foreign languages and cultures

    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_65k_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
     arcade
    0.49
    H
    0.47
    J
    0.47
    Quarter
    0.46
    M
    0.45
    F
    0.45
     unconscious
    0.44
    P
    0.44
    W
    0.44
    TO
    0.44
    POSITIVE LOGITS
     petrochemical
    0.45
    adaşlar
    0.45
     boissons
    0.44
    ieson
    0.42
    ajem
    0.42
    distance
    0.41
     sağlık
    0.41
    seguir
    0.41
    ikaner
    0.41
    eonium
    0.41
    Activations Density 0.013%

    No Known Activations