© 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. 10-GEMMASCOPE-RES-131K
    7. 58527
    Prev
    Next
    INDEX
    Explanations

    programming code and technical terms

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

    The neuron is detecting occurrences of the double-equals comparison operator (“==”).

    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
    瑨
    -2.88
    
    -2.84
    呖
    -2.72
    ↵↵
    -2.72
    摭
    -2.69
    इटम
    -2.52
    ୯
    -2.47
    LLocation
    -2.39
    ной
    -2.31
    瓩
    -2.31
    POSITIVE LOGITS
    ing
    3.80
    6
    2.66
    ة
    2.55
    8
    2.47
    0
    2.33
    3
    2.33
    ためには
    2.17
     relacionados
    2.16
    7
    2.13
    だいぶ
    2.09
    Activations Density 0.003%

    No Known Activations