© 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. 102383
    Prev
    Next
    INDEX
    Explanations

    music and sports teams

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

    The neuron consistently fires on occurrences of the word “Blues” (or “blues”), whether as a team name or music‐genre reference.

    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
    垕
    -3.31
    UGHTER
    -3.00
    焄
    -2.98
    哢
    -2.89
    jaqueta
    -2.86
    
    -2.78
    鰾
    -2.69
    泐
    -2.58
    
    -2.53
    퐼
    -2.53
    POSITIVE LOGITS
    or
    2.86
    $
    2.53
    H
    2.44
    سجيلات
    2.42
    L
    2.39
    B
    2.38
    E
    2.33
    {
    2.33
    A
    2.31
    “
    2.30
    Activations Density 0.004%

    No Known Activations