© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103608
    Prev
    Next
    INDEX
    Explanations

    comparing magnitudes and speeds

    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
     Dinas
    -1.57
     EVEN
    -1.32
    possibly
    -1.27
     WIL
    -1.22
     ij
    -1.17
    ྂ
    -1.16
     calefacción
    -1.16
    рино
    -1.15
     baterías
    -1.15
     SEVER
    -1.15
    POSITIVE LOGITS
     this
    2.11
     eight
    1.57
     seven
    1.55
     diligent
    1.55
     four
    1.54
     for
    1.51
     at
    1.50
     it
    1.50
     two
    1.50
     nine
    1.49
    Activations Density 0.133%

    No Known Activations