© 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. 22872
    Prev
    Next
    INDEX
    Explanations

    . starting new sentences

    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
    nă
    -1.46
    метров
    -1.41
    tiem
    -1.38
    Ṛ
    -1.34
    சு
    -1.33
    ++];
    -1.31
    maphore
    -1.30
    dien
    -1.30
    .'</
    -1.30
    скан
    -1.29
    POSITIVE LOGITS
     they
    1.74
    2
    1.52
     cercando
    1.47
     we
    1.41
     distintas
    1.34
     distintos
    1.28
    るので
    1.28
     this
    1.28
    みたいです
    1.27
     about
    1.25
    Activations Density 0.156%

    No Known Activations