© 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. 7530
    Prev
    Next
    INDEX
    Explanations

    URL paths and errors

    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
     that
    -1.54
     it
    -1.52
    機會
    -1.49
     osal
    -1.48
     each
    -1.41
    扪
    -1.41
     such
    -1.37
     截图
    -1.35
     who
    -1.34
    Максим
    -1.33
    POSITIVE LOGITS
    '
    2.25
     '
    1.60
     \"
    1.59
    ?}",
    1.41
     tendrá
    1.40
     почему
    1.34
     \
    1.34
     —
    1.32
     `
    1.31
    \_
    1.31
    Activations Density 0.115%

    No Known Activations