© 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. 59630
    Prev
    Next
    INDEX
    Explanations

    Jimi Hendrix or Browning

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

    The neuron fires most strongly on unusually long, multisyllabic tokens (e.g. “brownie,” “browning,” “pyrrolidine,” “trowel,” “Jimi,” “Hendrix”).

    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
    ’
    -3.23
     \
    -2.55
    は
    -2.38
     Adds
    -2.36
    戩
    -2.31
    乆
    -2.30
    蒾
    -2.22
     チキン
    -2.20
    ㌘
    -2.16
    いため
    -2.13
    POSITIVE LOGITS
    ◍
    2.28
     regards
    2.19
    图为
    2.09
    啻
    2.06
     kanskje
    1.98
    可以选择
    1.98
     deseos
    1.95
     protocolos
    1.94
    髣
    1.92
     imidlertid
    1.91
    Activations Density 0.005%

    No Known Activations