© 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. 12573
    Prev
    Next
    INDEX
    Explanations

    SLANT, Kleijn, Morna, Max, Flexport

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

    let me know

    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
     from
    0.46
     ہے۔
    0.45
     。
    0.43
    。
    0.40
     ।
    0.40
     可
    0.39
     ४
    0.38
     图
    0.38
     từ
    0.38
    。\
    0.38
    POSITIVE LOGITS
    га
    0.38
     vehement
    0.36
     rimane
    0.34
     berusaha
    0.33
     còn
    0.32
     Öffentlichkeit
    0.32
     wouldn
    0.32
    മതി
    0.32
     wronged
    0.32
     neće
    0.31
    Activations Density 0.015%

    No Known Activations