© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85329
    Prev
    Next
    INDEX
    Explanations

    two-photon spectroscopy

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

    The neuron activates on numeric tokens (both integers and decimals) in code or text.

    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
    </b>
    -2.02
     most
    -1.66
     for
    -1.60
    )
    -1.52
    %");
    -1.38
    ]=>
    -1.30
     compare
    -1.30
     was
    -1.27
     ۱۱
    -1.27
    ).
    -1.25
    POSITIVE LOGITS
     {
    
    
    1.48
    ILERS
    1.34
    idió
    1.33
     jossa
    1.28
     kvě
    1.27
     vulné
    1.26
    uoja
    1.24
    咙
    1.23
     of
    1.23
     čier
    1.23
    Activations Density 0.001%

    No Known Activations