© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12000
    Prev
    Next
    INDEX
    Explanations

    polygons and cycles

    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
     fortal
    -1.38
    korn
    -1.37
    \
    -1.33
     prosa
    -1.30
    place
    -1.30
    while
    -1.30
    либо
    -1.29
    逦
    -1.29
    ational
    -1.27
    that
    -1.27
    POSITIVE LOGITS
    guigu
    1.65
    bicicleta
    1.57
    </b>
    1.55
    azienda
    1.55
    laatst
    1.52
    funko
    1.48
    ὺς
    1.45
    alipay
    1.44
    鴣
    1.42
    🪅
    1.41
    Activations Density 0.054%

    No Known Activations