© 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. 78513
    Prev
    Next
    INDEX
    Explanations

    List A debut for Pakistan

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

    The neuron is detecting numeric data—especially years and other date-style numbers—typically found in biographical timeline entries.

    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
    Cinco
    -0.81
     påvir
    -0.75
    蠶
    -0.72
    Nations
    -0.71
    tilling
    -0.71
     cosmo
    -0.71
     zimowa
    -0.69
    Ranked
    -0.68
    Cabbage
    -0.68
    ECD
    -0.67
    POSITIVE LOGITS
     domestic
    1.23
     Domestic
    1.05
    Domestic
    0.99
    domestic
    0.94
     Ran
    0.90
     season
    0.90
     seasons
    0.86
     state
    0.83
     setState
    0.81
    州市
    0.81
    Activations Density 0.047%

    No Known Activations