© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116021
    Prev
    Next
    INDEX
    Explanations

    academic texts and proper nouns

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

    The neuron strongly activates on numerical tokens, especially standalone numbers and year‐like numerals.

    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
     Oral
    -0.77
     contemporánea
    -0.74
    ZH
    -0.73
     translated
    -0.72
    toolkit
    -0.71
    蹈
    -0.71
     Bình
    -0.69
     Vac
    -0.69
     ונ
    -0.68
    Oral
    -0.68
    POSITIVE LOGITS
     Romantic
    0.80
     participating
    0.77
     period
    0.73
    יהם
    0.72
    itious
    0.71
    projek
    0.71
     Gründ
    0.70
    迷
    0.70
     quelle
    0.69
    tabili
    0.69
    Activations Density 0.021%

    No Known Activations