© 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. 98565
    Prev
    Next
    INDEX
    Explanations

    date, version numbers

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

    The neuron strongly activates on multi‐digit numeric strings (e.g. three or more digits in a row such as long numeric attribute values).

    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
    ruckt
    -0.89
     only
    -0.83
     incorporating
    -0.81
     would
    -0.80
     mengakibatkan
    -0.79
    ächtige
    -0.79
     semi
    -0.77
    HttpPost
    -0.77
     may
    -0.76
     comprimidos
    -0.76
    POSITIVE LOGITS
     مكتبه
    1.12
    Ҹ
    0.84
    Specialized
    0.81
     gewählt
    0.80
     紫色
    0.79
    ུ་
    0.79
    Ꮋ
    0.78
     ALP
    0.77
    ardio
    0.77
     prequel
    0.77
    Activations Density 0.000%

    No Known Activations