© 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. 54337
    Prev
    Next
    INDEX
    Explanations

    articles after "the" or "that"

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

    breakdown, explanation, comprehensive

    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
    a
    0.37
     birinci
    0.34
    [
    0.30
    Meta
    0.29
     The
    0.29
     Celia
    0.29
     Preliminary
    0.28
     soltanto
    0.28
     Terminator
    0.28
     Katherine
    0.28
    POSITIVE LOGITS
     BSData
    0.34
    ᆻ
    0.32
     কৌ
    0.31
    왤
    0.31
    ারন
    0.31
    樞
    0.30
    瑩
    0.30
    ளிர்
    0.30
    ಂದ್ರ
    0.30
     ancients
    0.30
    Activations Density 0.090%

    No Known Activations