© 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. 143986
    Prev
    Next
    INDEX
    Explanations

    international languages

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

    thread or hexagons

    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
    і
    0.53
    agini
    0.52
     since
    0.50
    ifiers
    0.50
    agens
    0.49
    c
    0.49
    algam
    0.49
    itures
    0.48
    gic
    0.48
    ut
    0.47
    POSITIVE LOGITS
     جري
    0.54
     Verständ
    0.54
     கல்
    0.52
    Languages
    0.51
     Steward
    0.49
     ميل
    0.48
     yönet
    0.47
    Coding
    0.47
     kategorie
    0.47
     ታ
    0.46
    Activations Density 0.000%

    No Known Activations