© 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. 48917
    Prev
    Next
    INDEX
    Explanations

    HTTP methods

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

    The neuron primarily activates on tokens that contain digits (i.e. numeric literals).

    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
     geographic
    -0.87
    catid
    -0.82
    Khach
    -0.82
    playera
    -0.79
     geom
    -0.79
     možno
    -0.76
     場面
    -0.76
    HttpPut
    -0.75
     góc
    -0.75
    Слайд
    -0.75
    POSITIVE LOGITS
    HEAD
    1.29
     HEAD
    1.03
    options
    1.02
    Options
    1.00
    delete
    1.00
    head
    1.00
     OPTIONS
    0.98
     post
    0.97
     delete
    0.93
     Delete
    0.93
    Activations Density 0.006%

    No Known Activations