© 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. 72617
    Prev
    Next
    INDEX
    Explanations

    Lyapunov related words

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates strongly on the term “Lyapunov exponent” (and its variants), i.e. occurrences of “Lyapunov exponent(s).”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    嫫
    -3.41
     a
    -3.28
    镚
    -3.02
     dopo
    -2.61
    </em>
    -2.44
     MUCH
    -2.42
     neuen
    -2.38
     MOST
    -2.36
    
    -2.31
    на
    -2.30
    POSITIVE LOGITS
    鵟
    2.52
    archiwizowane
    2.52
    filas
    2.50
     باسلام
    2.47
     تھے
    2.42
     広場
    2.36
    ዬ
    2.36
    鱟
    2.34
    べし
    2.30
    ﾖ
    2.30
    Activations Density 0.015%

    No Known Activations