© 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. 136723
    Prev
    Next
    INDEX
    Explanations

    you get

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

    serving, retrieving, or identifying structures

    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
     vielen
    0.46
    MenuBar
    0.44
     Obwohl
    0.43
    ENGINE
    0.43
    ">
    0.42
    auml
    0.42
     غر
    0.42
     أوروب
    0.42
     ALPINE
    0.42
    te
    0.42
    POSITIVE LOGITS
    愼
    0.50
    λασ
    0.48
     smartphone
    0.45
     gunakan
    0.45
    राधना
    0.45
    ्रेड
    0.44
    肛
    0.43
     лично
    0.43
     sequestration
    0.43
    ில்லியன்
    0.42
    Activations Density 0.004%

    No Known Activations