© 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. 129558
    Prev
    Next
    INDEX
    Explanations

    The neuron is chiefly detecting numeric values and mathematical‐style number expressions.

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

    chemical compounds and financial terms

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

    mathematical expressions with exponents and operators.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     astute
    -0.91
    Samson
    -0.85
     suminist
    -0.85
     kalite
    -0.84
    acier
    -0.84
     occurrences
    -0.83
    בוצ
    -0.83
     core
    -0.83
     ejercer
    -0.81
     duża
    -0.79
    POSITIVE LOGITS
     brasil
    0.86
    Ζ
    0.82
    風險
    0.82
     affaire
    0.81
    RelativeTo
    0.79
     ?',
    0.77
    joyed
    0.76
     Tole
    0.73
    ديو
    0.73
    Хорошо
    0.73
    Activations Density 0.049%

    No Known Activations