© 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. 128297
    Prev
    Next
    INDEX
    Explanations

    types of products

    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
     män
    -1.23
    ÑO
    -1.23
    =?,
    -1.20
     حادث
    -1.17
    ర్య
    -1.17
    Только
    -1.16
    ubahan
    -1.16
     they
    -1.16
    ionados
    -1.16
     kumpulan
    -1.14
    POSITIVE LOGITS
     that
    1.55
     such
    1.52
     takich
    1.34
     takie
    1.34
     aceste
    1.30
     -
    1.27
     gesprochen
    1.27
     älteren
    1.25
     today
    1.22
     heutigen
    1.21
    Activations Density 0.427%

    No Known Activations