© 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. 86735
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

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

    The neuron fires on numeric tokens (dates, years, street or house numbers) in structured biographical or geographical 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
     sailed
    -0.83
    芭
    -0.80
    Mega
    -0.77
    저
    -0.71
     ドラゴン
    -0.68
    hpp
    -0.67
     պ
    -0.67
    Gross
    -0.66
    女主
    -0.65
     methamphetamine
    -0.65
    POSITIVE LOGITS
     Kerry
    1.14
    Kerry
    1.00
     Salzburg
    0.82
     Becher
    0.80
     Carrasco
    0.79
     ?”
    0.77
     montado
    0.75
    emper
    0.75
    وسف
    0.75
    legion
    0.74
    Activations Density 0.012%

    No Known Activations