© 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. 77814
    Prev
    Next
    INDEX
    Explanations

    major followed by noun/classification

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

    minor vs major classifications

    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
     Moż
    0.81
    ა
    0.81
    は
    0.79
     Ну
    0.76
     Prés
    0.75
     Bạn
    0.74
    는
    0.73
     Возможно
    0.73
     Má
    0.73
     Lí
    0.73
    POSITIVE LOGITS
    .
    1.10
    (
    0.96
    st
    0.73
    (.*
    0.70
     minor
    0.69
    Major
    0.67
     major
    0.64
    ,”
    0.63
    ups
    0.62
     uplifting
    0.61
    Activations Density 0.035%

    No Known Activations