© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81430
    Prev
    Next
    INDEX
    Explanations

    midi controller

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

    The neuron fires strongly on mentions of specific music‐technology product or protocol names (e.g. “Motif Rack,” “MIDI File,” “Live (8)”), model identifiers, and related technical terms.

    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
     걸
    -0.84
     Gandalf
    -0.78
     grunge
    -0.75
     Ralf
    -0.75
     Cartridge
    -0.73
     Pasa
    -0.73
     Newt
    -0.71
     Mersey
    -0.71
    Além
    -0.71
     தே
    -0.69
    POSITIVE LOGITS
     controller
    1.20
     controllers
    1.02
     controls
    0.99
     launching
    0.93
     controlling
    0.90
     control
    0.90
    controls
    0.88
    Controls
    0.86
     Controller
    0.85
     encoder
    0.84
    Activations Density 0.007%

    No Known Activations