© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10935
    Prev
    Next
    INDEX
    Explanations

    programming class definitions

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

    This neuron detects mentions of a code class whose name ends in “Base,” i.e. base-class identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    错
    0.55
    measure
    0.55
    menuid
    0.54
     Staples
    0.53
    융
    0.53
     staple
    0.52
    additive
    0.52
    拶
    0.52
    पर्यंत
    0.51
    ความ
    0.51
    POSITIVE LOGITS
     cuyas
    0.65
     cuyos
    0.64
     Bila
    0.63
     cuyo
    0.63
     sullo
    0.63
     ヴィンテージ
    0.63
    .".,
    0.61
     cujo
    0.60
     cuya
    0.60
     onDelete
    0.60
    Activations Density 0.000%

    No Known Activations