© 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. 15559
    Prev
    Next
    INDEX
    Explanations

    jump, jmp, function

    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
    \
    -2.23
     большую
    -2.11
    as
    -2.05
     
    -1.91
    蘼
    -1.89
    過ぎる
    -1.84
     olma
    -1.84
     diesem
    -1.84
    ere
    -1.80
    9
    -1.80
    POSITIVE LOGITS
     ſta
    2.44
    鲞
    2.30
    熥
    2.28
    ."
    2.27
     köln
    2.16
     männer
    2.14
    нией
    2.08
    ೖ
    2.08
     leaped
    2.06
     replete
    2.06
    Activations Density 0.001%

    No Known Activations