© 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. 34203
    Prev
    Next
    INDEX
    Explanations

    code assertion or naming context

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

    This neuron detects references to the JUnit testing framework, especially in import statements.

    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
    män
    -1.03
    étique
    -0.98
     чехол
    -0.96
     läsa
    -0.93
     می‌شوند
    -0.92
    maxx
    -0.90
     пнев
    -0.90
    gunakan
    -0.89
     енер
    -0.88
    ReadByte
    -0.88
    POSITIVE LOGITS
     remer
    1.02
     geringen
    1.00
     ninguno
    0.97
     segun
    0.97
    が表示
    0.96
     сказал
    0.95
    brought
    0.94
    strengthen
    0.93
    établissement
    0.93
     impot
    0.93
    Activations Density 0.000%

    No Known Activations