© 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. 6918
    Prev
    Next
    INDEX
    Explanations

    touchdown impact

    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
    -2.41
    hauled
    -2.19
    ſſel
    -2.00
    逦
    -1.98
    t
    -1.85
    the
    -1.83
     新款
    -1.81
    弭
    -1.79
    ton
    -1.78
     zaidi
    -1.71
    POSITIVE LOGITS
     coloridos
    2.14
    もちろん
    1.95
     anerkannt
    1.90
    趼
    1.88
    事も
    1.88
     beragam
    1.88
     wesentlich
    1.87
    と聞
    1.84
    هداف
    1.77
     estudian
    1.75
    Activations Density 0.001%

    No Known Activations