© 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. 100709
    Prev
    Next
    INDEX
    Explanations

    programming class names

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

    class names or identifiers in programming code, particularly in object-oriented contexts like services, controllers, mappers, and views.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code‐identifier tokens that name common software components—i.e. class or file suffixes like Service, Controller (Ctrl), Model, View, Route, Mapper, Utils, etc.

    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
     will
    -1.94
    érape
    -1.28
     and
    -1.27
    ！？
    -1.24
    áveis
    -1.24
    malade
    -1.17
    szak
    -1.16
    ੱਕ
    -1.13
    elance
    -1.12
     приготовить
    -1.12
    POSITIVE LOGITS
    これを
    1.43
     imprimer
    1.41
    Their
    1.35
    その他
    1.29
    Masukkan
    1.26
    difficult
    1.24
     этих
    1.22
     этого
    1.20
    ceğini
    1.16
    こういう
    1.14
    Activations Density 0.046%

    No Known Activations