© 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. 113135
    Prev
    Next
    INDEX
    Explanations

    Q: or "Me" or "Many" or "Pul"

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

    The neuron is highly activated by numeric tokens containing decimal points (i.e. floating-point numbers).

    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
     sommar
    -2.05
    ússia
    -1.99
     garantie
    -1.95
     motivadoras
    -1.86
     godk
    -1.82
     guapa
    -1.80
     gånger
    -1.78
    想
    -1.77
     brosse
    -1.74
     visst
    -1.72
    POSITIVE LOGITS
    .
    2.77
     is
    2.08
    </i>
    1.87
     now
    1.77
    ৢ
    1.70
     iu
    1.66
     was
    1.65
    又要
    1.64
    
    1.62
    
    1.62
    Activations Density 0.000%

    No Known Activations