© 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. 172306
    Prev
    Next
    INDEX
    Explanations

    documents, visits, or actions

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

    grading, rating, or scoring

    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
    oty
    0.45
    bilical
    0.44
     pedagogical
    0.42
    amba
    0.41
    ЛЬ
    0.41
     Pedagog
    0.41
    ibli
    0.41
    🐩
    0.41
    ewer
    0.40
    🐽
    0.40
    POSITIVE LOGITS
     رہتے
    0.47
     cuando
    0.45
     البيانات
    0.43
     ousted
    0.43
     quando
    0.42
     hapless
    0.42
     додат
    0.42
    监管
    0.41
     آخرین
    0.41
    )،
    0.41
    Activations Density 0.001%

    No Known Activations