© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71567
    Prev
    Next
    INDEX
    Explanations

    hearing questions or oneself asked

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

    The neuron activates specifically on occurrences of the word “hear.”

    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
    m
    -2.88
    ஂ
    -2.75
     و
    -2.70
     We
    -2.66
     और
    -2.63
    婞
    -2.63
     і
    -2.61
    which
    -2.55
    i
    -2.50
    ですし
    -2.47
    POSITIVE LOGITS
    B
    2.88
     we
    2.55
     glimpses
    2.50
    僦
    2.39
     plenty
    2.39
     hear
    2.39
     firsthand
    2.39
     hoher
    2.38
     penchant
    2.30
     großes
    2.28
    Activations Density 0.013%

    No Known Activations