© 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. 171976
    Prev
    Next
    INDEX
    Explanations

    reasons and placement information

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

    create content

    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
    ঞ্জার
    0.64
    মোঃ
    0.53
    aný
    0.50
    𝗡
    0.49
     jobNumber
    0.49
    জমেন্ট
    0.48
    𝗙
    0.48
    ন্ড
    0.48
     claire
    0.48
    𐰖
    0.47
    POSITIVE LOGITS
     reason
    0.50
    itet
    0.48
    orems
    0.47
    iten
    0.46
    idy
    0.45
    asons
    0.45
    iqui
    0.45
    adik
    0.44
    ẹ
    0.44
    it
    0.44
    Activations Density 0.001%

    No Known Activations