© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57718
    Prev
    Next
    INDEX
    Explanations

    stomp boxes and pedals

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

    The neuron strongly responds to mentions of guitar effects pedals or “stompbox” model names.

    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
     الحكومة
    -0.88
    гут
    -0.82
    сылка
    -0.78
     Venkates
    -0.76
     chatbot
    -0.75
     gramos
    -0.75
    kJ
    -0.75
     št
    -0.75
    гота
    -0.75
     lokale
    -0.74
    POSITIVE LOGITS
     pedal
    2.23
     pedals
    1.88
     Pedal
    1.60
     foots
    1.53
    pedal
    1.48
     stomp
    1.38
    Ped
    1.20
     foot
    1.19
     PED
    1.01
     ped
    1.00
    Activations Density 0.013%

    No Known Activations