© 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. 44220
    Prev
    Next
    INDEX
    Explanations

    device at, down into, you can, it to, that looks, Some fashionable, it February, there ., all are, it risks

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

    privacy, professional, educational, scientific

    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
     क्यों
    0.47
     вследствие
    0.45
     若
    0.45
    ይታ
    0.42
     작업을
    0.40
     작업
    0.40
     정의역
    0.40
    不想
    0.39
     ভুগ
    0.39
     зависит
    0.39
    POSITIVE LOGITS
    為
    0.50
    proud
    0.48
     خبری
    0.46
     بڑی
    0.46
    กับ
    0.46
     automobiles
    0.45
     باي
    0.45
     violators
    0.44
     billionaires
    0.44
     vehicles
    0.43
    Activations Density 0.000%

    No Known Activations