© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
     kuhusu
    -1.54
     nying
    -1.53
    iramente
    -1.45
    ımız
    -1.42
    ïlande
    -1.39
    
    -1.39
     baada
    -1.35
    ioon
    -1.34
    phère
    -1.33
    peut
    -1.32
    POSITIVE LOGITS
     in
    1.94
     all
    1.79
     endforeach
    1.71
     the
    1.50
     with
    1.47
    all
    1.34
     -
    1.34
     всех
    1.30
     semua
    1.27
    ⃙
    1.27
    Activations Density 0.073%

    No Known Activations