© 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. 10-GEMMASCOPE-RES-131K
    7. 129274
    Prev
    Next
    INDEX
    Explanations

    Gottlieb Ridge frey VA Police

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

    The neuron flags capitalized single-word proper nouns—names of people, places, or specialized entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ！”
    -3.30
    !”
    -2.36
    錚
    -2.30
     prominent
    -2.28
     discernible
    -2.14
    ！（
    -2.13
    𝐭
    -2.13
    墻
    -2.13
     eight
    -2.08
    
    -2.05
    POSITIVE LOGITS
     Therefore
    2.91
    轳
    2.63
     But
    2.56
     Nevertheless
    2.36
     Moreover
    2.36
    訁
    2.30
    饹
    2.25
     However
    2.20
     ‘’
    2.20
     Similarly
    2.17
    Activations Density 0.042%

    No Known Activations