© 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. 44650
    Prev
    Next
    INDEX
    Explanations

    clearly or obviously

    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
     Также
    -1.63
    IERRA
    -1.62
    <>
    -1.58
     Instead
    -1.57
    zied
    -1.55
     Additionally
    -1.53
    </b>
    -1.53
     would
    -1.50
    ização
    -1.49
     Nevertheless
    -1.49
    POSITIVE LOGITS
    いました
    1.55
    ↵↵
    1.52
     breite
    1.48
     gehouden
    1.41
     zweite
    1.39
    𝜑
    1.39
    に行って
    1.36
    '
    1.34
     französische
    1.33
    ,\\
    1.30
    Activations Density 0.015%

    No Known Activations