© 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. 68213
    Prev
    Next
    INDEX
    Explanations

    comes from different sources

    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
    </i>
    -1.47
    -1.41
    one
    -1.30
     davidson
    -1.30
    this
    -1.29
     administ
    -1.28
     Toscana
    -1.27
    another
    -1.26
    at
    -1.24
     gonz
    -1.23
    POSITIVE LOGITS
     regulación
    1.55
    тельностью
    1.41
     estren
    1.40
    了什么
    1.36
     zespo
    1.35
     vidrio
    1.35
     yayınları
    1.33
     baloncesto
    1.32
     lidé
    1.31
     cuenca
    1.31
    Activations Density 0.052%

    No Known Activations