© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91439
    Prev
    Next
    INDEX
    Explanations

    the band name

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

    The neuron is detecting major proper nouns—especially titles and artist or album names—in a music infobox or list context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    боры
    -0.81
    рек
    -0.78
     pará
    -0.78
    戏
    -0.76
     agra
    -0.76
    romo
    -0.74
    ỏi
    -0.74
    боров
    -0.74
    usia
    -0.73
     garner
    -0.73
    POSITIVE LOGITS
     Rolling
    1.32
     Beatles
    1.09
    Rolling
    1.06
     Stones
    1.06
     Pret
    0.99
     Grateful
    0.98
     Replace
    0.96
     Pog
    0.96
    Traveling
    0.93
    mişti
    0.92
    Activations Density 0.047%

    No Known Activations