© 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. 91577
    Prev
    Next
    INDEX
    Explanations

    code comments and labels

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

    The neuron strongly activates on standalone numeric tokens (e.g. version numbers, years, IDs).

    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
    tq
    -0.76
    TRAIL
    -0.75
     Klavier
    -0.69
     doğum
    -0.69
     オブ
    -0.67
    alco
    -0.66
    PRESSION
    -0.66
    Cet
    -0.65
    ield
    -0.65
    SocketAddress
    -0.65
    POSITIVE LOGITS
    バナナ
    0.65
    錯誤
    0.63
     بیشتر
    0.63
     Deane
    0.63
    Doctors
    0.63
     Bancroft
    0.62
    riam
    0.61
     XLS
    0.61
    ذا
    0.61
     ثابت
    0.60
    Activations Density 0.062%

    No Known Activations