© 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. 22-GEMMASCOPE-RES-131K
    7. 129299
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens—any isolated numbers or numeric values in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    match scores or specific names/items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Occasionally
    -0.91
    BURG
    -0.89
     講
    -0.84
    خص
    -0.82
     Preparatory
    -0.79
    仅仅
    -0.79
    TLE
    -0.78
    Pre
    -0.78
     stava
    -0.78
     erstes
    -0.78
    POSITIVE LOGITS
     and
    0.93
     então
    0.91
     then
    0.87
    arı
    0.86
     nak
    0.85
    Affect
    0.85
    SizeMode
    0.84
    があると
    0.84
    ˀ
    0.84
    ="&#
    0.83
    Activations Density 0.003%

    No Known Activations