© 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. 58062
    Prev
    Next
    INDEX
    Explanations

    departments and affiliations

    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
     Every
    -2.50
     This
    -2.47
     Whether
    -2.27
     Because
    -2.22
     Perhaps
    -2.13
     These
    -2.13
     Each
    -2.06
     Regardless
    -2.05
     That
    -2.05
     What
    -2.05
    POSITIVE LOGITS
    粜
    2.78
     a
    2.39
    圌
    2.34
    ឵
    2.28
    瘜
    2.13
    ჻
    2.08
    〬
    2.02
    ⎆
    2.02
    орк
    2.02
     خودش
    2.02
    Activations Density 0.030%

    No Known Activations