© 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. 229576
    Prev
    Next
    INDEX
    Explanations

    sale, lbs, offer, charities, artwork, magazine

    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
     फिल्म
    0.44
     ফিল্ম
    0.44
    矾
    0.43
    aughter
    0.42
     tangan
    0.41
     فیلم
    0.41
    responsive
    0.40
     airliner
    0.40
    éc
    0.40
    ak
    0.40
    POSITIVE LOGITS
     cristianos
    0.50
    كتب
    0.49
    清除
    0.49
    訒
    0.47
     newsletters
    0.46
    綀
    0.46
    書籍
    0.46
     cleaners
    0.45
    чиго
    0.45
    謃
    0.44
    Activations Density 0.000%

    No Known Activations