© 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. 244517
    Prev
    Next
    INDEX
    Explanations

    services and charges

    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
    it
    0.63
    at
    0.56
    Section
    0.50
    S
    0.46
    0.45
    સ
    0.45
    is
    0.43
    Search
    0.42
    ab
    0.42
    within
    0.42
    POSITIVE LOGITS
     comunicazione
    0.48
    かに
    0.47
     рэгістра
    0.47
    jobSize
    0.46
    ுகள்
    0.46
     संचार
    0.45
     ন্যায
    0.45
     تفسیر
    0.45
    埥
    0.45
     რომლებიც
    0.45
    Activations Density 0.001%

    No Known Activations