© 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. 1597
    Prev
    Next
    INDEX
    Explanations

    US locations and specific places

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

    The neuron is primarily picking up standalone numbers and numeric tokens (e.g. years, measurements, 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
     thing
    -0.95
     anvil
    -0.70
    kitten
    -0.70
    tbl
    -0.69
    ROSE
    -0.69
    𝐆
    -0.69
     Advertise
    -0.68
    JEL
    -0.68
     balık
    -0.68
     rq
    -0.67
    POSITIVE LOGITS
     Brunswick
    0.97
    Brunswick
    0.89
     Freeport
    0.77
    iddharth
    0.73
    taminophen
    0.72
     Monmouth
    0.71
    AGAN
    0.71
     chor
    0.71
    人参
    0.70
     ſet
    0.68
    Activations Density 0.030%

    No Known Activations