© 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. 236562
    Prev
    Next
    INDEX
    Explanations

    buy or sell listings

    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
    س
    0.61
    ن
    0.55
    ه‌های
    0.49
     Parse
    0.48
    أ
    0.48
    دل
    0.48
    pulse
    0.47
    暧
    0.47
    parse
    0.47
    و
    0.47
    POSITIVE LOGITS
    henburg
    0.46
    MENU
    0.46
     homogen
    0.45
     palazzo
    0.45
     abnormal
    0.43
     quiescent
    0.43
     motiva
    0.43
    igenza
    0.42
     modern
    0.42
     rodeo
    0.42
    Activations Density 0.000%

    No Known Activations