© 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. 39320
    Prev
    Next
    INDEX
    Explanations

    band, group, or project

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

    The neuron activates on mentions of musical-artist classifications—terms that identify an act’s format or genre (e.g. band, trio, rapper, electronic rock, pop, etc.).

    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
     will
    -1.54
     for
    -1.39
     costs
    -1.35
     was
    -1.32
     many
    -1.31
     useful
    -1.29
     use
    -1.27
     when
    -1.23
     while
    -1.23
     valuable
    -1.21
    POSITIVE LOGITS
     recomendable
    1.52
     Trabalho
    1.36
    pires
    1.32
     tatuagens
    1.30
    1.28
    voer
    1.28
    moiselle
    1.28
    lllllllll
    1.27
     Eſ
    1.27
     oluştur
    1.27
    Activations Density 0.087%

    No Known Activations