© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    karaoke, laryngectomy, cappella

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

    The neuron strongly activates on mentions of karaoke and related singing terms (e.g., “karaoke,” “singing,” “KTV”).

    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
    舠
    -2.58
    饪
    -2.48
    '
    -2.42
    
    -2.17
     {
    -2.17
     you
    -2.14
     \
    -2.05
    ),
    -2.00
     meget
    -2.00
     färg
    -1.97
    POSITIVE LOGITS
    妯
    2.23
     karaoke
    2.11
    ྅
    2.11
    沨
    2.11
    写真を撮
    2.11
    ⛥
    2.05
    ции
    2.05
    вей
    2.02
    ᥬ
    2.02
     土産
    2.00
    Activations Density 0.002%

    No Known Activations