© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176276
    Prev
    Next
    INDEX
    Explanations

    awards and cabinet positions

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

    historical forecasts and development estimates

    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
    Negative Logits
     plaats
    0.46
     macht
    0.46
     lä
    0.45
     lätt
    0.44
     দাঁ
    0.43
    ))$,
    0.43
     răng
    0.43
    >${
    0.43
    erville
    0.43
    >):
    0.43
    POSITIVE LOGITS
     commend
    0.48
    Supreme
    0.47
    Blessed
    0.46
    یا
    0.46
    comend
    0.45
    ера
    0.45
    Exerc
    0.43
    нора
    0.43
     سع
    0.42
    Para
    0.42
    Activations Density 0.000%

    No Known Activations