© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57065
    Prev
    Next
    INDEX
    Explanations

    age of

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

    The neuron activates on numeric tokens (numbers and measurements) embedded 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
     ofthe
    -1.01
     della
    -0.98
    還有
    -0.81
    OfThe
    -0.76
    ofthe
    -0.74
     in
    -0.73
     DELLA
    -0.71
     schlechte
    -0.68
    年に
    -0.68
    もはや
    -0.67
    POSITIVE LOGITS
     of
    1.84
    bnd
    0.83
     ће
    0.80
     endroits
    0.78
    وار
    0.77
    **********
    0.77
    kömm
    0.74
     Mě
    0.74
    ***********
    0.73
     HÀ
    0.73
    Activations Density 0.080%

    No Known Activations