© 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. 40521
    Prev
    Next
    INDEX
    Explanations

    config and configuration

    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
     to
    -1.70
    </h2>
    -1.61
     conocidos
    -1.55
     pesados
    -1.49
     gs
    -1.45
     rapidamente
    -1.45
    냑
    -1.38
    蟶
    -1.37
    鏟
    -1.37
     abbreviated
    -1.37
    POSITIVE LOGITS
     and
    2.22
     should
    1.65
     although
    1.55
    除了
    1.52
    ariate
    1.48
     because
    1.42
     ongeveer
    1.41
     good
    1.40
     did
    1.38
     all
    1.34
    Activations Density 0.015%

    No Known Activations