© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117601
    Prev
    Next
    INDEX
    Explanations

    numbers, digits, and punctuation

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

    The neuron strongly activates on standalone numeric tokens (i.e. numbers in tables or queries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    (!__
    -1.07
    ݣ
    -0.98
     птицы
    -0.97
    日閲覧
    -0.94
     and
    -0.94
     berbeda
    -0.90
     مختلف
    -0.90
     וכן
    -0.87
     funkci
    -0.86
    
    -0.86
    POSITIVE LOGITS
     которым
    1.01
    1
    0.95
    </td>
    0.95
    a
    0.95
    </strong>
    0.93
    ric
    0.89
    </b>
    0.89
    采用了
    0.87
    ()");
    0.85
    だけ
    0.85
    Activations Density 0.009%

    No Known Activations