© 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. 22692
    Prev
    Next
    INDEX
    Explanations

    software application

    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
    硨
    -3.63
     kredi
    -3.30
     illustre
    -3.13
     pittores
    -2.94
    埽
    -2.89
     empat
    -2.88
     tabak
    -2.81
     akade
    -2.78
     artisti
    -2.77
    蠖
    -2.73
    POSITIVE LOGITS
    ஂ
    3.59
    焄
    3.33
    1
    3.11
    幾天
    3.09
     vorliegenden
    3.00
    ↵
    2.97
    ...”
    2.92
    灕
    2.84
    紧接着
    2.83
     betreffenden
    2.80
    Activations Density 0.045%

    No Known Activations