© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    maxima, minima, and Stevens

    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
    榈
    -3.08
    龊
    -2.95
    櫚
    -2.55
     \_
    -2.36
    "
    -2.27
    owulf
    -2.14
    ’
    -2.11
    ⸰
    -2.08
    ین
    -2.03
     būtų
    -2.03
    POSITIVE LOGITS
    </h1>
    3.00
     Its
    2.94
    你这个
    2.64
    B
    2.59
    {
    2.56
    mathrm
    2.47
     Importantly
    2.44
    इटम
    2.42
     When
    2.41
    釤
    2.31
    Activations Density 0.008%

    No Known Activations