© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

    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
     If
    -2.30
    li
    -1.93
    ”:
    -1.90
     They
    -1.89
     This
    -1.88
     There
    -1.84
     Here
    -1.83
    ”).
    -1.78
     llego
    -1.75
     possono
    -1.74
    POSITIVE LOGITS
    癀
    2.03
    ющего
    1.87
    딤
    1.81
    塤
    1.78
    Tôi
    1.75
    nemer
    1.73
     essas
    1.69
    蛧
    1.66
     niña
    1.66
    暃
    1.64
    Activations Density 0.067%

    No Known Activations