© 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. 139285
    Prev
    Next
    INDEX
    Explanations

    work and its contexts

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

    work and its contexts

    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
    3
    0.80
    ت
    0.67
    w
    0.64
    4
    0.64
    in
    0.62
    การ
    0.60
    ل
    0.59
    ir
    0.58
    5
    0.57
    art
    0.55
    POSITIVE LOGITS
    슨
    0.61
    स्थल
    0.56
    はず
    0.55
     diferenci
    0.55
     lembra
    0.55
     giocando
    0.55
     saludable
    0.54
    🍢
    0.54
    قة
    0.53
    fulness
    0.53
    Activations Density 0.041%

    No Known Activations