© 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. 130229
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens (especially multi‐digit numbers) in text.

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

    list-based items and numbering

    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
     that
    -1.47
     of
    -1.38
    }$.
    -1.26
    ”。
    -1.25
    Ayrıca
    -1.23
     atau
    -1.20
     לְ
    -1.17
     spørs
    -1.13
    琑
    -1.13
     OGSÅ
    -1.12
    POSITIVE LOGITS
     ensuing
    1.03
     большин
    1.01
     minnie
    0.98
     kendisi
    0.96
     Præ
    0.96
     Cæsar
    0.96
     Cæ
    0.94
    ське
    0.94
     rca
    0.94
    NOVEMBER
    0.94
    Activations Density 0.041%

    No Known Activations