© 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. 26342
    Prev
    Next
    INDEX
    Explanations

    Eastern, dart, file paths

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

    The neuron activates on tokens containing numeric digits, i.e. it detects number tokens.

    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
     both
    -1.12
     since
    -1.05
     in
    -0.95
     considerably
    -0.93
     slightly
    -0.93
     those
    -0.90
     whole
    -0.87
    -0.86
     bré
    -0.84
     viewDid
    -0.84
    POSITIVE LOGITS
     aynı
    1.03
     verhind
    0.99
     лы
    0.88
     maakt
    0.87
    niad
    0.86
     esplor
    0.86
     usarlo
    0.86
     ido
    0.85
    其他
    0.85
    ۔۔
    0.85
    Activations Density 0.171%

    No Known Activations