© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16567
    Prev
    Next
    INDEX
    Explanations

    named entities and places

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

    The neuron fires on common function words that introduce prepositional phrases (e.g. “on,” “through,” “into,” “out,” “in,” “as,” “from”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     esportivo
    -1.06
     нов
    -0.99
     perfeito
    -0.99
     DRAIN
    -0.97
    ountain
    -0.97
    ebly
    -0.97
     vinto
    -0.95
    üglich
    -0.94
    )|(
    -0.92
    嚶
    -0.92
    POSITIVE LOGITS
     their
    1.62
    olsom
    0.97
    LogUtil
    0.96
    泗
    0.94
    reszcie
    0.93
     the
    0.93
     loro
    0.92
     که
    0.91
     їх
    0.91
     majd
    0.91
    Activations Density 0.126%

    No Known Activations