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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99828
    Prev
    Next
    INDEX
    Explanations

    Introduction or headings like it

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

    The neuron is specifically detecting numeric literals (sequences of digits) in code and 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
     heartache
    -0.65
    orale
    -0.65
     Antrim
    -0.64
     angin
    -0.64
     Sad
    -0.62
     اعمال
    -0.62
     democracy
    -0.61
    memoized
    -0.60
    ونس
    -0.60
     terrorism
    -0.59
    POSITIVE LOGITS
    HP
    0.75
     имеется
    0.74
     имеются
    0.73
    umes
    0.72
    alam
    0.69
    HBox
    0.68
    heen
    0.68
    ocino
    0.68
     پرداخت
    0.67
    říklad
    0.67
    Activations Density 0.059%

    No Known Activations