© 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. 22-GEMMASCOPE-RES-131K
    4. 11082
    Prev
    Next
    INDEX
    Explanations

    musical tastes and listening

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

    The neuron detects words and phrases about discovering, exploring, and broadening one’s musical tastes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     with
    -1.41
     السياس
    -1.38
     staff
    -1.30
    ApJ
    -1.27
     cost
    -1.27
     costs
    -1.24
    green
    -1.24
     feasibility
    -1.18
    "';
    -1.18
     actions
    -1.15
    POSITIVE LOGITS
    entraî
    1.38
     magnifiques
    1.35
    Література
    1.35
     nouveautés
    1.34
     goû
    1.34
     jaka
    1.33
     پروفایل
    1.32
     gada
    1.27
    wakili
    1.27
    ographical
    1.27
    Activations Density 0.054%

    No Known Activations