© 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. 65432
    Prev
    Next
    INDEX
    Explanations

    contributor license agreements

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

    The neuron activates on numeric tokens (digits and version numbers) in the text.

    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
     endblock
    -0.92
     Zeiss
    -0.77
    viana
    -0.76
    ográficas
    -0.73
    Ʋ
    -0.73
    “……”
    -0.71
    tioners
    -0.71
     visit
    -0.71
     robust
    -0.69
    Filtro
    -0.69
    POSITIVE LOGITS
    loria
    0.69
    儆
    0.65
    клон
    0.64
     axis
    0.63
    Basin
    0.63
     dl
    0.63
     spazio
    0.62
     THINK
    0.62
    rede
    0.61
     NPR
    0.61
    Activations Density 0.044%

    No Known Activations