© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108493
    Prev
    Next
    INDEX
    Explanations

    foreign language interjections

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

    The neuron activates on multi‐digit numeric tokens (long 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_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
    '
    -2.05
     with
    -2.03
     that
    -1.84
     because
    -1.83
     (
    -1.80
     as
    -1.80
     by
    -1.76
    と
    -1.76
     in
    -1.72
     most
    -1.69
    POSITIVE LOGITS
    すっ
    1.89
    えっ
    1.80
    久し
    1.79
    䊐
    1.76
    の方に
    1.75
     trám
    1.74
    
    1.70
     deſt
    1.70
     rése
    1.69
    髎
    1.68
    Activations Density 0.172%

    No Known Activations