© 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. 77586
    Prev
    Next
    INDEX
    Explanations

    code markers and keywords

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

    the neuron strongly activates on numeric tokens, i.e. digits and 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
    becker
    -0.79
    Luxembourg
    -0.78
    дри
    -0.78
    Belgium
    -0.76
    పు
    -0.75
    られていた
    -0.73
    ◓
    -0.73
    coln
    -0.71
    nische
    -0.71
    shiro
    -0.71
    POSITIVE LOGITS
     shop
    0.96
     Shop
    0.88
    Analyte
    0.86
     支
    0.83
     Suez
    0.81
     разбира
    0.77
    หมด
    0.75
     El
    0.75
     バッグ
    0.75
    |^{
    0.74
    Activations Density 0.000%

    No Known Activations