© 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. 64289
    Prev
    Next
    INDEX
    Explanations

    equality and comparison operators

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

    This neuron fires on uppercase identifiers and keywords—especially class/method names or SQL operators (e.g. LIKE, String, StartsWith, EndsWith).

    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
    thargy
    -1.23
    badah
    -1.11
     저장
    -1.09
     soucis
    -1.08
     bedankt
    -1.05
     pozna
    -1.04
     terminer
    -1.02
    に触
    -1.02
    Retour
    -1.02
     penser
    -1.02
    POSITIVE LOGITS
     if
    1.12
     or
    1.07
     isinstance
    1.04
     ….
    0.97
     with
    0.94
     you
    0.94
     „
    0.93
    Mediabestanden
    0.93
     they
    0.92
     reverse
    0.90
    Activations Density 0.020%

    No Known Activations