© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1208
    Prev
    Next
    INDEX
    Explanations

    identifiers and data fields

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

    The neuron strongly activates on code‐style tokens—e.g. function/command names, data‐type identifiers, and other programming/parameter keywords.

    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_31_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
     オーバー
    0.56
     吸
    0.53
     フル
    0.52
     Якщо
    0.51
     Қ
    0.51
     這
    0.51
     技術
    0.51
     ৪৮
    0.50
    Ḥ
    0.49
     灯
    0.49
    POSITIVE LOGITS
     userId
    0.89
    userId
    0.75
     id
    0.73
     name
    0.66
     userid
    0.64
     userID
    0.63
     userName
    0.63
     username
    0.61
     userInput
    0.61
     sessionId
    0.61
    Activations Density 0.001%

    No Known Activations