© 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. 37678
    Prev
    Next
    INDEX
    Explanations

    book size descriptor

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

    essential programming terms

    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
     obicei
    0.46
     avendo
    0.45
    ;
    0.44
     local
    0.44
     nutric
    0.43
    িনিয়র
    0.43
    콕
    0.42
     fiscal
    0.42
     cheery
    0.42
     ovvero
    0.42
    POSITIVE LOGITS
     మూ
    0.49
     Kofi
    0.49
    溏
    0.48
    ur
    0.48
    odies
    0.47
     épars
    0.47
     Cappadocia
    0.47
    ām
    0.46
    ounded
    0.46
    omyel
    0.45
    Activations Density 0.000%

    No Known Activations