© 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. 34-GEMMASCOPE-RES-131K
    7. 81229
    Prev
    Next
    INDEX
    Explanations

    vector array, DstarLite, store request, speech recognition, support binary

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

    The neuron is triggered by code‐style tokens and formatting—e.g. backticks, tildes, asterisks, underscores, slashes and code identifiers—i.e. it detects inline code or code‐block markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ขับ
    -0.76
     ні
    -0.74
     Brunnen
    -0.71
    সূত্র
    -0.69
    Modules
    -0.69
     dared
    -0.69
     Modules
    -0.68
    尙
    -0.67
    小程序
    -0.66
     Ávila
    -0.65
    POSITIVE LOGITS
     robot
    1.08
    Robot
    0.87
    robot
    0.87
     Robot
    0.86
     ik
    0.84
     kalend
    0.81
     robotic
    0.79
     moves
    0.79
    монт
    0.78
     满
    0.76
    Activations Density 0.007%

    No Known Activations