© 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. 219677
    Prev
    Next
    INDEX
    Explanations

    prevent making, Document Delivery, Modern furniture

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

    parts of speech and structure

    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
     as
    0.62
    citizens
    0.51
     coupon
    0.51
    as
    0.50
    s
    0.47
    striatis
    0.46
     inclusiv
    0.46
     membre
    0.45
    inse
    0.45
     died
    0.45
    POSITIVE LOGITS
     அளிக்க
    0.44
    撑
    0.43
     مزاج
    0.43
    プローチ
    0.42
     раск
    0.42
    讲解
    0.42
    Wie
    0.42
    支撑
    0.40
    Pong
    0.40
     Mitchell
    0.40
    Activations Density 0.000%

    No Known Activations