© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31934
    Prev
    Next
    INDEX
    Explanations

    sound volume and loudness

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

    The neuron activates on mentions of audio volume controls and level adjustments (e.g. “volume,” “turn up,” “levels,” “listening devices”).

    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
    vains
    -0.81
    pecial
    -0.78
    illar
    -0.77
    ^{*}\
    -0.76
     speedy
    -0.74
    )*(
    -0.73
     особы
    -0.73
    ThroughAttribute
    -0.71
    特殊的
    -0.71
     Slow
    -0.71
    POSITIVE LOGITS
     loud
    2.69
     louder
    2.48
     volume
    2.20
    loud
    2.02
     Loud
    1.88
     гром
    1.86
     LOU
    1.85
    音量
    1.84
    Loud
    1.82
    volume
    1.77
    Activations Density 0.025%

    No Known Activations