© 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. 34-GEMMASCOPE-RES-131K
    7. 59306
    Prev
    Next
    INDEX
    Explanations

    wind instruments

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

    The neuron triggers strongly on hyphenated compound adjectives describing technical physical specifications (e.g. “cylindrical-bore,” “double-reed”)

    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
     paint
    -0.96
     paints
    -0.93
    PAINT
    -0.83
     Schilder
    -0.77
     Paint
    -0.77
    悍
    -0.77
     flute
    -0.76
    cusa
    -0.73
     Primal
    -0.73
     perverse
    -0.72
    POSITIVE LOGITS
     Clarinet
    0.96
     klar
    0.93
     clarinet
    0.90
    Clar
    0.85
     clar
    0.77
    Klar
    0.76
    functioning
    0.75
    klar
    0.72
     lemn
    0.71
     chal
    0.70
    Activations Density 0.038%

    No Known Activations