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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45258
    Prev
    Next
    INDEX
    Explanations

    status, getStatus, setStatus

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

    This neuron responds to numeric tokens (numbers and digit sequences) in code or comments.

    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
    manie
    -0.90
     incarnation
    -0.86
     กระ
    -0.86
     registered
    -0.82
     stesso
    -0.81
    itve
    -0.78
    vestre
    -0.77
    titas
    -0.77
     mismo
    -0.76
    рез
    -0.75
    POSITIVE LOGITS
     status
    1.20
    status
    1.03
    Status
    0.98
    estatus
    0.95
     Status
    0.93
    getStatus
    0.91
     STATUS
    0.91
     setStatus
    0.88
    地位
    0.87
    STATUS
    0.87
    Activations Density 0.005%

    No Known Activations