© 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. 112702
    Prev
    Next
    INDEX
    Explanations

    parameter in code

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

    the word "parameter" or "Parameter" in programming code contexts.

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

    The neuron fires on occurrences of the term “parameter” (and its morphological variants) in code or documentation.

    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
    是
    -3.23
     但
    -3.16
    )
    -3.00
    价格
    -2.88
    鬭
    -2.80
    新加坡
    -2.59
    孭
    -2.59
    ꜄
    -2.50
    dijual
    -2.48
    时间
    -2.47
    POSITIVE LOGITS
    稣
    3.86
    ).
    3.13
    箆
    3.11
    </h3>
    3.09
    趼
    3.06
    所说的
    2.83
    ):
    2.81
    )
    2.78
    紧接着
    2.66
    翆
    2.64
    Activations Density 0.016%

    No Known Activations