© 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. 22-GEMMASCOPE-RES-131K
    7. 130405
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens representing numeric values (i.e. numbers and numeric literals).

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

    JSON keys and values

    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
     this
    -1.23
     znaleźć
    -1.01
     итоге
    -0.98
     keç
    -0.97
    ędzynarod
    -0.95
     their
    -0.94
     rác
    -0.92
     Landschafts
    -0.91
    iked
    -0.88
     latter
    -0.87
    POSITIVE LOGITS
     veterin
    0.98
    loyment
    0.97
    ISLAM
    0.92
    anae
    0.91
     רוצה
    0.89
    กับ
    0.89
     ambass
    0.89
    Ile
    0.89
    Ѡ
    0.88
     circu
    0.88
    Activations Density 0.003%

    No Known Activations