© 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. 238327
    Prev
    Next
    INDEX
    Explanations

    life, cleaning, battery, years, understand, apps

    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
    жие
    0.48
     DHCP
    0.47
     ингреди
    0.47
     Transvaal
    0.47
     SIGNIFIC
    0.47
    मंड
    0.46
    盥
    0.46
    드시
    0.45
     substr
    0.44
     landsc
    0.44
    POSITIVE LOGITS
    ğin
    0.53
    robot
    0.49
    ęp
    0.49
    princess
    0.48
     สม
    0.48
    luk
    0.46
     ว
    0.46
    typ
    0.46
     ท
    0.46
     ช
    0.45
    Activations Density 0.000%

    No Known Activations