© 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. 7048
    Prev
    Next
    INDEX
    Explanations

    opentelemetry and code includes

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

    This neuron fires on code-like tokens—identifiers, punctuation (e.g. parentheses), and version numbers or other technical snippets.

    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
     จาก
    0.68
     От
    0.65
     พ
    0.65
     ନ
    0.63
     ต
    0.63
     г
    0.59
     от
    0.58
     黃
    0.58
     mwaka
    0.58
     Да
    0.57
    POSITIVE LOGITS
    Entity
    0.70
    adapter
    0.67
    Object
    0.66
    Serialized
    0.66
    DTO
    0.65
    pojo
    0.65
    DataObject
    0.64
    listener
    0.64
    Runnable
    0.64
    executor
    0.63
    Activations Density 0.000%

    No Known Activations