© 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. 169436
    Prev
    Next
    INDEX
    Explanations

    numbers following options or time

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

    math problems, equations

    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
    iever
    0.49
    所以
    0.48
     結果
    0.48
     +
    0.47
     Therefore
    0.45
    intervals
    0.45
    izes
    0.44
     所以
    0.44
     concludes
    0.44
    candidates
    0.43
    POSITIVE LOGITS
     просто
    0.55
     simplesmente
    0.50
     gewoon
    0.48
     ஏனெ
    0.47
    ט
    0.47
     보시면
    0.47
     முழுக்க
    0.47
    טו
    0.46
     bunların
    0.45
     일단
    0.45
    Activations Density 0.000%

    No Known Activations