© 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. 84967
    Prev
    Next
    INDEX
    Explanations

    headphone amp

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

    The neuron strongly activates on numeric tokens or alphanumeric identifiers (e.g. model numbers, version numbers, or any token containing digits).

    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
    ___]
    -0.82
    moine
    -0.77
    água
    -0.75
    弦
    -0.73
    立即
    -0.72
    alow
    -0.71
     könnte
    -0.71
     lokasi
    -0.70
    警察
    -0.70
     rekord
    -0.68
    POSITIVE LOGITS
     DAC
    1.30
     headphone
    1.15
     portable
    1.04
     gain
    0.98
     amp
    0.95
    DAC
    0.94
     powerless
    0.93
     Head
    0.91
     desktop
    0.90
     Zap
    0.88
    Activations Density 0.012%

    No Known Activations