© 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. 101478
    Prev
    Next
    INDEX
    Explanations

    product categories and descriptions

    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
    Angebot
    -1.77
     portanto
    -1.71
    אם
    -1.66
     októ
    -1.63
     trám
    -1.62
    שלום
    -1.59
    Schüler
    -1.59
     Empieza
    -1.58
    slika
    -1.57
    goblin
    -1.57
    POSITIVE LOGITS
     in
    2.05
     that
    1.95
    :
    1.82
     this
    1.70
     also
    1.65
     &
    1.61
     so
    1.59
     on
    1.45
     but
    1.43
     etc
    1.43
    Activations Density 0.005%

    No Known Activations