© 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. 78704
    Prev
    Next
    INDEX
    Explanations

    names of people and places

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

    The neuron strongly activates on standalone numeric values or years (especially high-precision numbers) typically found in structured data like infoboxes, tables, or citation/reference lists.

    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
     phosp
    -0.84
    acão
    -0.83
    )$-
    -0.83
     acestea
    -0.82
     THOUGH
    -0.80
     पो
    -0.80
    ()}>
    -0.80
    Ň
    -0.80
    ológica
    -0.79
     occured
    -0.79
    POSITIVE LOGITS
    麋
    0.79
     yen
    0.76
     реально
    0.74
     rode
    0.73
     mooi
    0.72
     mettent
    0.72
    至此
    0.72
    /*++
    0.72
    '<
    0.71
    上手
    0.70
    Activations Density 0.650%

    No Known Activations