© 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. 15341
    Prev
    Next
    INDEX
    Explanations

    three years / structures of / product model

    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
     could
    -1.72
     can
    -1.67
     still
    -1.62
     gives
    -1.59
     might
    -1.58
     makes
    -1.57
     allows
    -1.55
     encourages
    -1.52
     will
    -1.47
     attempting
    -1.47
    POSITIVE LOGITS
     darm
    1.64
     lande
    1.60
     męska
    1.57
    recently
    1.56
     damski
    1.52
     męski
    1.49
    atical
    1.48
    yeah
    1.48
    amazing
    1.46
     maat
    1.45
    Activations Density 0.014%

    No Known Activations