© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39375
    Prev
    Next
    INDEX
    Explanations

    code assertion and equality checks

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

    The neuron fires on unit‐test assertion or checking calls (e.g., “assert”, “CHECK”, “deepEqual”, “equal”, “toBe”, etc.).

    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
    dekor
    -1.13
     ideen
    -1.06
    ancang
    -1.04
    hingga
    -1.00
    denk
    -0.98
     komfor
    -0.97
    medik
    -0.96
    }());
    -0.95
    juries
    -0.95
    cfm
    -0.94
    POSITIVE LOGITS
     incluso
    1.09
     четырех
    1.06
     местных
    1.00
     acepción
    0.96
     decir
    0.95
     nejen
    0.94
    食べ物
    0.94
     beider
    0.92
    ニア
    0.92
     southeastern
    0.92
    Activations Density 0.004%

    No Known Activations