© 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. 156078
    Prev
    Next
    INDEX
    Explanations

    tablets debossed

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

    Ideally

    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
     స
    0.50
    ining
    0.50
     ಅಗ
    0.47
     ಕಾರ
    0.47
    anners
    0.47
     alley
    0.46
     る
    0.46
     eateries
    0.45
     intersections
    0.45
     よく
    0.45
    POSITIVE LOGITS
     présents
    0.51
    porque
    0.49
    ائلة
    0.48
     nových
    0.47
    绁
    0.47
    Ｉ
    0.47
     transmissão
    0.46
    сү
    0.46
     препаратов
    0.46
    يله
    0.46
    Activations Density 0.003%

    No Known Activations