© 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. 200052
    Prev
    Next
    INDEX
    Explanations

    Link in bio!

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

    original unique novel

    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
    N
    0.50
    aty
    0.46
    рян
    0.45
    num
    0.44
    utto
    0.44
    ple
    0.43
    D
    0.43
    wendungen
    0.43
     Chalk
    0.42
    いった
    0.42
    POSITIVE LOGITS
     sexe
    0.51
     accompagnée
    0.49
     spéciale
    0.49
     Phòng
    0.49
     fontos
    0.49
     ۴
    0.48
    🥩
    0.48
     ٢
    0.48
     csp
    0.48
     sexually
    0.47
    Activations Density 0.000%

    No Known Activations