© 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. 59695
    Prev
    Next
    INDEX
    Explanations

    class definitions and structure

    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
    </h2>
    -1.70
     musikk
    -1.63
     after
    -1.52
     will
    -1.48
     or
    -1.44
    2
    -1.44
     ideen
    -1.44
     måneder
    -1.44
    f
    -1.38
    6
    -1.38
    POSITIVE LOGITS
     habilitar
    1.70
     angesehen
    1.64
    ICOLON
    1.63
     curar
    1.60
     cercano
    1.59
     ajustar
    1.58
     desactivar
    1.57
     Debido
    1.55
     撮っ
    1.54
     zowel
    1.52
    Activations Density 0.128%

    No Known Activations