© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    reflecting or based on context

    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
     навы
    0.47
    lüğ
    0.46
    zinho
    0.45
    𝐨
    0.45
    ز
    0.44
    坠
    0.44
     แม
    0.44
     ไม
    0.43
     نمبر
    0.43
     трябва
    0.43
    POSITIVE LOGITS
     cranberries
    0.50
    Õ
    0.49
    prima
    0.49
     charges
    0.48
     Closer
    0.47
     reports
    0.46
    ’
    0.46
    week
    0.45
     Asset
    0.44
     Allianz
    0.44
    Activations Density 0.000%

    No Known Activations