© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    numbers and specific entities

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

    Spanish and Catalan

    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
     bunu
    0.33
     noção
    0.30
    躹
    0.29
     човек
    0.28
     þat
    0.28
     bhaj
    0.28
    嫐
    0.28
     atleast
    0.27
    浬
    0.27
     intros
    0.27
    POSITIVE LOGITS
    ic
    0.32
     University
    0.29
    iz
    0.29
     Wikimedia
    0.28
     Согласно
    0.28
    ol
    0.28
    *,
    0.28
    um
    0.27
    According
    0.27
    Согласно
    0.27
    Activations Density 0.373%

    No Known Activations