© 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. 96909
    Prev
    Next
    INDEX
    Explanations

    government contracts, legal matters

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

    preparation and subsequent actions

    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
     žena
    0.48
     Using
    0.46
    Swing
    0.46
     Waffen
    0.45
    jš
    0.44
     Nashville
    0.43
    transferases
    0.43
    +","+
    0.42
     insanların
    0.42
    ミルク
    0.41
    POSITIVE LOGITS
    이며
    0.46
     ज्यात
    0.43
    이었다
    0.42
    MOT
    0.42
    今日も
    0.42
    퀴
    0.42
     응
    0.41
    ༨
    0.41
     waarin
    0.41
    걱
    0.41
    Activations Density 0.001%

    No Known Activations