© 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. 95845
    Prev
    Next
    INDEX
    Explanations

    Star Wars and Inglourious Basterds

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

    contrast or concession

    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
    o
    0.52
    л
    0.48
    악
    0.47
     påver
    0.46
    槭
    0.45
    ుడు
    0.44
    y
    0.44
     муниципа
    0.43
    우
    0.43
    呂
    0.43
    POSITIVE LOGITS
     directement
    0.54
     direttamente
    0.47
     coisa
    0.46
     truly
    0.46
     réellement
    0.45
    wallet
    0.45
     conversa
    0.45
    té
    0.44
    IM
    0.43
     meille
    0.43
    Activations Density 0.001%

    No Known Activations