© 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. 72562
    Prev
    Next
    INDEX
    Explanations

    observer in code contexts

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

    The neuron fires on occurrences of “Observer” or related observing keywords, i.e. it detects mentions of observer‐pattern classes or APIs.

    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
    1
    -3.22
    .”
    -2.64
     was
    -2.55
    
    -2.45
     flurry
    -2.28
    )
    -2.28
     The
    -2.23
    5
    -2.22
    即使
    -2.17
    或者
    -2.16
    POSITIVE LOGITS
    ⦊
    2.69
    鹟
    2.66
    ❉
    2.45
    櫪
    2.42
    铪
    2.38
    鳜
    2.31
    狆
    2.28
    نین
    2.27
    ه
    2.25
    ቍ
    2.22
    Activations Density 0.003%

    No Known Activations