© 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. 236147
    Prev
    Next
    INDEX
    Explanations

    points, Crews, beauty

    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
    的选择
    0.50
    豊富
    0.50
    。「
    0.48
    をと
    0.48
    。
    0.45
    ，
    0.44
    IPAL
    0.44
     दिलीप
    0.42
    を用
    0.41
    ुए
    0.41
    POSITIVE LOGITS
     حالات
    0.47
     teilweise
    0.45
    ك
    0.43
    atello
    0.43
    藍
    0.43
     zumindest
    0.42
     llor
    0.42
    تد
    0.42
     blueberries
    0.42
     Karriere
    0.42
    Activations Density 0.001%

    No Known Activations