© 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. 10-GEMMASCOPE-RES-131K
    7. 47636
    Prev
    Next
    INDEX
    Explanations

    music record labels

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

    The neuron specializes in detecting mentions of music record labels and related label/distribution 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_10/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
     policia
    -1.83
     infal
    -1.80
     persua
    -1.76
     estancias
    -1.69
    libatkan
    -1.64
    ڱ
    -1.64
     zitate
    -1.63
     milano
    -1.63
    kių
    -1.60
     remun
    -1.58
    POSITIVE LOGITS
    to
    1.84
    ’
    1.83
    wide
    1.83
     ‘
    1.79
    la
    1.71
     “
    1.70
     estavam
    1.70
     hacen
    1.69
    —
    1.67
    ve
    1.63
    Activations Density 0.026%

    No Known Activations