© 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. 22-GEMMASCOPE-RES-131K
    7. 72361
    Prev
    Next
    INDEX
    Explanations

    citations with parentheses

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

    This neuron does not respond to any tokens (it remains inactive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    будь
    -0.95
     fulfills
    -0.91
     является
    -0.86
    gemeen
    -0.85
     artikkelen
    -0.84
     sustains
    -0.84
    columnwidth
    -0.83
     panoramique
    -0.82
    条件
    -0.81
     муніципалі
    -0.81
    POSITIVE LOGITS
     these
    1.03
     собрать
    1.02
    erver
    0.96
     '${
    0.95
     stance
    0.95
     proches
    0.95
    暧
    0.95
     worin
    0.94
    valve
    0.94
    oj
    0.94
    Activations Density 0.002%

    No Known Activations