© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60732
    Prev
    Next
    INDEX
    Explanations

    numbers including 100

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

    The neuron strongly activates on numeric tokens (i.e. standalone numbers or digit sequences).

    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
    Finalmente
    -0.83
     Kitz
    -0.76
     таки
    -0.75
    скільки
    -0.74
     murmured
    -0.73
    ambique
    -0.73
     Belts
    -0.73
    FRAGMENT
    -0.71
     編集
    -0.69
    聡
    -0.69
    POSITIVE LOGITS
     Ve
    0.79
    ylase
    0.78
     gleichen
    0.78
     IDENTITY
    0.77
    urende
    0.77
     настоящее
    0.75
    чним
    0.74
     지
    0.74
    rona
    0.73
    ellos
    0.73
    Activations Density 0.026%

    No Known Activations