© 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. 10-GEMMASCOPE-RES-131K
    7. 9012
    Prev
    Next
    INDEX
    Explanations

    music jam sessions

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

    The neuron fires on mentions of musical “sessions” and “jams” (e.g. “jam session,” “jamming,” “playback session”).

    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
     you
    -1.80
     to
    -1.50
     help
    -1.46
    It
    -1.41
    Is
    -1.40
    慙
    -1.37
    ve
    -1.36
     need
    -1.34
    m
    -1.34
     inalámb
    -1.32
    POSITIVE LOGITS
    кой
    1.48
    
    1.47
     kialak
    1.42
     nyelven
    1.35
     jellemző
    1.33
     készült
    1.33
     akár
    1.31
     inconn
    1.30
     slay
    1.30
    பி
    1.29
    Activations Density 0.023%

    No Known Activations