© 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. 10-GEMMASCOPE-RES-131K
    4. 105347
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

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

    function parameter lists and variable declarations in code, particularly focusing on the opening parenthesis and comma separators between parameters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting PHP variable‐name tokens marked by the “$” prefix.

    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
     gustar
    -1.58
     your
    -1.48
     it
    -1.41
     帅气
    -1.41
     our
    -1.40
    stones
    -1.39
     Чтобы
    -1.39
    ଃ
    -1.38
    یریت
    -1.37
     maanden
    -1.37
    POSITIVE LOGITS
    </h2>
    1.55
    在他
    1.44
    </
    1.33
    ");
    1.32
    所以我
    1.29
    ()))
    
    1.27
    中国
    1.27
    }{
    1.27
    在她
    1.27
    </h6>
    1.26
    Activations Density 0.017%

    No Known Activations