© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38366
    Prev
    Next
    INDEX
    Explanations

    Newtonsoft, htt, Schwarzenberg, Polynesian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    تیجه
    -2.77
    什么的
    -2.64
    Thirty
    -2.45
    蹀
    -2.44
    岨
    -2.33
    禟
    -2.30
     новую
    -2.25
    也算是
    -2.22
    待って
    -2.20
     perte
    -2.16
    POSITIVE LOGITS
    ו
    2.53
    銥
    2.36
    釭
    2.23
    i
    2.22
    頎
    2.19
    <
    2.17
    ၟ
    2.16
    it
    2.14
    n
    2.06
    疍
    1.98
    Activations Density 0.002%

    No Known Activations