© 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. 58226
    Prev
    Next
    INDEX
    Explanations

    Tanzania, Perkins, Vicki, Polytechnic, Macedonia

    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
    1
    -2.75
    2
    -2.75
    みたら
    -2.48
    8
    -2.47
    4
    -2.47
    みよう
    -2.34
    開始
    -2.34
     اشار
    -2.33
    9
    -2.30
    6
    -2.30
    POSITIVE LOGITS
     is
    2.69
    ة
    2.67
    .
    2.64
    蚡
    2.53
    n
    2.44
     wohin
    2.22
     Realität
    2.22
    蛩
    2.13
    ↵
    2.11
    tsz
    2.09
    Activations Density 0.005%

    No Known Activations