© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29394
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ົ້າ
    0.38
    ’
    0.38
    ಡುವುದ
    0.38
     obliga
    0.36
     favours
    0.35
     curva
    0.35
     เด่น
    0.35
     boasted
    0.35
     احسن
    0.35
     rupani
    0.35
    POSITIVE LOGITS
    وز
    0.40
     Glas
    0.38
     Uml
    0.38
     privacy
    0.38
    ⅳ
    0.37
     Mets
    0.36
     Knight
    0.36
     liter
    0.36
    մ
    0.36
     তারিখে
    0.35
    Activations Density 0.024%

    No Known Activations