© 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. 85605
    Prev
    Next
    INDEX
    Explanations

    expatriate or parametrized

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

    The neuron fires on standalone numeric tokens (digit sequences) in the 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
    ጺ
    -2.73
    ?’
    -2.59
    ⭓
    -2.48
    嚒
    -2.44
    ftrag
    -2.42
    ሖ
    -2.33
    🧏
    -2.31
    unicaciones
    -2.30
    ſſel
    -2.30
     encuentros
    -2.30
    POSITIVE LOGITS
    >
    3.42
    
    3.03
     
    2.77
     However
    2.52
    1
    2.47
     sucedió
    2.42
    <em>
    2.27
     únicamente
    2.25
    o
    2.20
     While
    2.14
    Activations Density 0.002%

    No Known Activations