© 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. 99997
    Prev
    Next
    INDEX
    Explanations

    quantities of types

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

    The neuron fires on numeric monetary amounts (e.g. “$ 25.75 million,” “billions of dollars”).

    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
    镲
    -1.95
    琲
    -1.88
     appelés
    -1.69
    
    -1.68
    ᕱ
    -1.68
    
    -1.66
    嗵
    -1.65
     traducción
    -1.65
     destinée
    -1.63
    饃
    -1.61
    POSITIVE LOGITS
     of
    2.36
    </h2>
    1.98
     outstanding
    1.80
     on
    1.75
     in
    1.69
     new
    1.66
     offers
    1.59
     added
    1.56
    </em>
    1.46
     easily
    1.46
    Activations Density 0.011%

    No Known Activations