© 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. 10-GEMMASCOPE-RES-131K
    7. 45400
    Prev
    Next
    INDEX
    Explanations

    the cause was argued

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

    The neuron specifically fires on occurrences of the word “cause.”

    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
    s
    -2.11
     is
    -2.08
     and
    -2.03
     after
    -1.75
     から
    -1.72
     because
    -1.69
     can
    -1.67
     sintomi
    -1.66
     when
    -1.64
     if
    -1.63
    POSITIVE LOGITS
    Excellent
    1.91
    Choosing
    1.89
    衚
    1.70
     superbes
    1.69
    gså
    1.69
     گرف
    1.68
    If
    1.67
    鬭
    1.66
    >
    1.66
    厹
    1.64
    Activations Density 0.032%

    No Known Activations