© 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. 45289
    Prev
    Next
    INDEX
    Explanations

    programming comments and code snippets

    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
    1
    -2.27
    e
    -2.08
    8
    -2.06
    2
    -1.98
    ut
    -1.85
    𓋼
    -1.81
    5
    -1.81
     hacer
    -1.78
    4
    -1.75
    al
    -1.64
    POSITIVE LOGITS
     is
    2.03
     '
    1.89
     tacón
    1.88
     semuanya
    1.82
    lección
    1.82
     wherein
    1.80
    puma
    1.79
     Hinblick
    1.77
    
    1.75
    </em>
    1.74
    Activations Density 0.079%

    No Known Activations