© 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. 22-GEMMASCOPE-RES-131K
    7. 66748
    Prev
    Next
    INDEX
    Explanations

    quoted song titles

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

    The neuron is highly activated by tokens that appear within or immediately around quoted song (or track) titles.

    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
    P
    -1.06
     سعر
    -1.01
    It
    -1.00
     напряжения
    -0.98
    小学生
    -0.98
    for
    -0.97
     verbunden
    -0.94
     pantaloni
    -0.94
    下一步
    -0.94
    /*!
    -0.93
    POSITIVE LOGITS
     which
    1.49
     other
    1.25
     from
    1.23
     provoque
    1.21
    vereignty
    1.17
     prêtre
    1.16
     sèche
    1.16
    ofing
    1.16
     written
    1.16
     song
    1.16
    Activations Density 0.035%

    No Known Activations