© 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. 64422
    Prev
    Next
    INDEX
    Explanations

    checking for null or empty

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

    This neuron activates on conditional‐expression tokens, e.g. “if” and comparison operators (==, ===) in code.

    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
     to
    -1.05
     for
    -1.01
     from
    -0.91
     Pesquisa
    -0.89
     with
    -0.88
     at
    -0.84
     so
    -0.84
     more
    -0.84
     other
    -0.83
     if
    -0.81
    POSITIVE LOGITS
     repuesto
    1.11
     registrada
    1.01
     mezi
    0.97
    textwidth
    0.94
     caractères
    0.92
    ATURE
    0.92
    呤
    0.91
     élas
    0.90
    kset
    0.90
     pratiquement
    0.89
    Activations Density 0.002%

    No Known Activations