© 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. 33398
    Prev
    Next
    INDEX
    Explanations

    Apache License, function, allow

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

    The neuron is picking out numeric tokens (strings of digits) whenever they appear in 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
    ්‍ර
    -0.82
    Fermi
    -0.79
    Authentic
    -0.79
    Catholic
    -0.77
     seba
    -0.77
    晰
    -0.77
    几何
    -0.77
    жного
    -0.77
    лене
    -0.76
    بوس
    -0.75
    POSITIVE LOGITS
    luv
    0.91
    Lass
    0.87
    lenia
    0.85
    )}-\
    0.77
    fter
    0.76
    uda
    0.76
     nowoczes
    0.75
    ufort
    0.75
     sorghum
    0.75
    ync
    0.75
    Activations Density 0.002%

    No Known Activations