© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82814
    Prev
    Next
    INDEX
    Explanations

    copyright notices and license information

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

    The neuron fires on numeric tokens (multi‐digit numbers) 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_34/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
    结尾
    -0.73
     }?>
    -0.71
    Tor
    -0.70
     tangerang
    -0.69
    ública
    -0.69
    STOR
    -0.69
     analys
    -0.67
    reras
    -0.65
     commis
    -0.65
     تواند
    -0.65
    POSITIVE LOGITS
     steigen
    0.72
    々は
    0.69
    dic
    0.67
    czny
    0.66
     formal
    0.63
    uttg
    0.63
     Produktions
    0.63
     rose
    0.63
    lanations
    0.62
     Martins
    0.62
    Activations Density 0.067%

    No Known Activations