© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11077
    Prev
    Next
    INDEX
    Explanations

    getClass, heterochromatin, properties

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

    Java reflection method calls, particularly 'getClass' and related class introspection methods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on uncommon, domain‐specific “jargon” tokens—e.g. camel-case code identifiers, annotation names, scientific or chemical terms, and proper names.

    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
     he
    -3.63
    趼
    -2.50
     The
    -2.50
    ࿚
    -2.38
     gesamte
    -2.31
     obsolete
    -2.25
     letzte
    -2.25
     curtail
    -2.20
     ehemalige
    -2.19
    не
    -2.16
    POSITIVE LOGITS
    鼱
    3.16
     殼
    2.73
     剧照
    2.73
     mengucapkan
    2.72
     litri
    2.67
    țiile
    2.61
    鐃
    2.59
    鷙
    2.53
    泚
    2.50
    稞
    2.44
    Activations Density 0.000%

    No Known Activations