© 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. 22-GEMMASCOPE-RES-131K
    7. 73978
    Prev
    Next
    INDEX
    Explanations

    data parsing and scripting

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

    The neuron fires on numeric tokens, i.e. it detects numbers (digits or numeric literals) 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_22/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
    Ales
    -0.95
    Kirche
    -0.84
    reiten
    -0.83
    Cuer
    -0.82
    einf
    -0.81
    Stry
    -0.78
     самому
    -0.77
     dicas
    -0.77
     gespannt
    -0.77
     決定
    -0.77
    POSITIVE LOGITS
    ('
    0.89
     tickets
    0.85
    lső
    0.81
    数据
    0.80
    citation
    0.79
    いなかった
    0.79
     requests
    0.78
     salvación
    0.78
     significados
    0.78
     across
    0.77
    Activations Density 0.056%

    No Known Activations