© 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. 10-GEMMASCOPE-RES-131K
    7. 15027
    Prev
    Next
    INDEX
    Explanations

    names or abbreviations followed by specific context

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

    The neuron strongly activates on individual capitalized tokens that serve as proper names (people, places, or other named 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
    ଃ
    -2.88
    缡
    -2.72
    翾
    -2.61
    ◬
    -2.59
    棐
    -2.55
    怂
    -2.50
    阋
    -2.48
    ྾
    -2.45
    עים
    -2.45
     They
    -2.41
    POSITIVE LOGITS
    }$
    4.03
     mostrar
    2.70
    та
    2.69
     мои
    2.69
    al
    2.69
    ⚋
    2.66
    鼱
    2.64
     esempi
    2.63
    可以
    2.59
    '
    2.55
    Activations Density 0.056%

    No Known Activations