© 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. 7305
    Prev
    Next
    INDEX
    Explanations

    SoundCloud and music platforms

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

    This neuron detects tokens in mentions of online media platforms or URLs (e.g., “on,” “http,” domain names like “soundcloud,” and similar link components).

    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
     Yahoo
    -0.80
     kalk
    -0.79
     COLON
    -0.73
    MessageId
    -0.71
    Chats
    -0.69
    nostic
    -0.68
    ピアノ
    -0.67
    Yahoo
    -0.66
    Matin
    -0.66
     saper
    -0.66
    POSITIVE LOGITS
     Sound
    3.05
     SoundCloud
    2.95
    Sound
    2.77
     sound
    2.34
    soundcloud
    2.33
    SOUND
    1.85
     SOUND
    1.78
    sound
    1.67
     Bandcamp
    1.66
    cloud
    1.48
    Activations Density 0.050%

    No Known Activations