© 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. 68451
    Prev
    Next
    INDEX
    Explanations

    Montgomery County and names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    是
    -3.05
    的
    -2.80
     unſ
    -2.77
    q
    -2.61
    section
    -2.52
    j
    -2.50
    A
    -2.48
    in
    -2.44
    2
    -2.42
     With
    -2.41
    POSITIVE LOGITS
    嵎
    3.45
    ᮣ
    2.94
     apolog
    2.81
    ⤥
    2.78
    玧
    2.75
    
    2.70
     einige
    2.70
    
    2.67
    ൎ
    2.61
    攫
    2.55
    Activations Density 0.002%

    No Known Activations