© 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. 74201
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    std
    -1.11
    setBounds
    -0.96
    stderr
    -0.94
    ᴺ
    -0.93
    goto
    -0.92
    ⩕
    -0.90
    なのか
    -0.90
    generally
    -0.88
    orsch
    -0.88
    iously
    -0.88
    POSITIVE LOGITS
    股票
    0.98
    abay
    0.98
     čet
    0.96
     sirvió
    0.90
    textAlignment
    0.88
    Bayer
    0.88
    niei
    0.87
     murky
    0.87
     sultry
    0.87
     zusätz
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.