© 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. 251725
    Prev
    Next
    INDEX
    Explanations

    version of

    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
     scra
    0.50
    resolution
    0.50
     flight
    0.48
     scriv
    0.48
    flight
    0.48
    ץ
    0.48
     sandpaper
    0.46
    
    0.46
     CCSDT
    0.45
    σή
    0.44
    POSITIVE LOGITS
    我们在
    0.46
    一组
    0.45
    献
    0.44
    活动
    0.43
    历史上
    0.43
    随着
    0.42
    所谓
    0.42
    差异
    0.42
     예배
    0.42
    现状
    0.42
    Activations Density 0.000%

    No Known Activations