© 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. 196595
    Prev
    Next
    INDEX
    Explanations

    notary stamps

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

    avoiding filler words, saving money, primary school

    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
     vár
    0.47
     Gründe
    0.44
    ോദ
    0.43
     निराशा
    0.42
    ourism
    0.42
    weather
    0.42
    زاده
    0.41
    現
    0.41
     odgov
    0.40
     integrante
    0.40
    POSITIVE LOGITS
     Bundestag
    0.46
     вокруг
    0.46
    Assemblée
    0.45
    чан
    0.44
     искусства
    0.43
     gebruiken
    0.43
     Володимир
    0.41
     Владимира
    0.40
     poprzez
    0.39
     Winfrey
    0.39
    Activations Density 0.001%

    No Known Activations