© 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. 68133
    Prev
    Next
    INDEX
    Explanations

    code or script delimiters

    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
    !
    -2.28
     angen
    -2.00
     kopf
    -1.94
     mög
    -1.92
     kön
    -1.90
     münchen
    -1.88
     a
    -1.86
     gewi
    -1.84
     puramente
    -1.83
     maquiagem
    -1.81
    POSITIVE LOGITS
    ("")]
    1.84
     to
    1.81
    ittà
    1.63
     основ
    1.61
    atigable
    1.60
     in
    1.59
    invokeLater
    1.59
    {~
    1.58
    makeConstraints
    1.56
    які
    1.56
    Activations Density 0.130%

    No Known Activations