© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80779
    Prev
    Next
    INDEX
    Explanations

    scheduling or tasks

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ﺮ
    0.51
     کردیا
    0.50
    不已
    0.50
    ровать
    0.49
    罗
    0.44
     Speaking
    0.44
     ہوگئی
    0.44
     Hình
    0.44
    Indeed
    0.43
    ])),
    0.43
    POSITIVE LOGITS
    őt
    0.45
    agré
    0.44
     lend
    0.43
     mauvais
    0.43
     (
    0.42
     len
    0.42
    sld
    0.42
    átor
    0.42
     inger
    0.42
    lement
    0.42
    Activations Density 0.000%

    No Known Activations