© 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. 56071
    Prev
    Next
    INDEX
    Explanations

    historical data bias

    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
     tolerancia
    0.46
    ائية
    0.45
     decrypt
    0.44
     présenté
    0.43
     partake
    0.43
    ᱗
    0.43
     заявление
    0.43
     decomposition
    0.42
    テナンス
    0.42
     MacDonald
    0.42
    POSITIVE LOGITS
    S
    0.54
    w
    0.54
    Š
    0.52
    r
    0.50
    hr
    0.50
    p
    0.49
    ف
    0.48
    F
    0.48
    פ
    0.48
     były
    0.47
    Activations Density 0.002%

    No Known Activations