© 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. 60276
    Prev
    Next
    INDEX
    Explanations

    SoundCloud tracks

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

    The neuron fires on URL‐style tokens, especially domain names like “soundcloud” and “.com.”

    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
     视频
    -0.82
    Britt
    -0.80
    vrolet
    -0.78
    kq
    -0.77
    Phyllis
    -0.75
     проє
    -0.75
    Fredrik
    -0.74
    Locking
    -0.73
     gehouden
    -0.73
     Video
    -0.73
    POSITIVE LOGITS
     waveform
    1.06
     waveforms
    1.03
    soundcloud
    0.96
     SoundCloud
    0.96
     listener
    0.95
     track
    0.91
     tracks
    0.90
    Permalink
    0.85
     Wave
    0.81
     limites
    0.78
    Activations Density 0.012%

    No Known Activations