© 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. 76890
    Prev
    Next
    INDEX
    Explanations

    foreign language or prayers

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

    ability to understand complex issues

    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
    9
    0.52
    eq
    0.48
    1
    0.47
    8
    0.47
    7
    0.46
    出了
    0.45
    Up
    0.44
    biggr
    0.43
    up
    0.41
     यूनाइटेड
    0.41
    POSITIVE LOGITS
     tunique
    0.51
    🖉
    0.51
     lundi
    0.50
    ⵄ
    0.50
    sommets
    0.50
     জানার
    0.49
     idéale
    0.48
    linhas
    0.48
    น
    0.48
     técnica
    0.47
    Activations Density 0.000%

    No Known Activations