© 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. 10019
    Prev
    Next
    INDEX
    Explanations

    sdk

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

    references to software development kits (SDKs) in file paths and code, particularly when followed by version numbers or path separators.

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

    The neuron detects occurrences of “SDK” (in any casing) within tokens, especially in file paths and identifiers.

    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
     That
    -2.20
     "
    -2.05
     Not
    -1.83
    主要的
    -1.81
    。"
    -1.80
    ）」
    -1.76
     stately
    -1.74
    ,
    -1.74
    玏
    -1.73
    बाइल
    -1.66
    POSITIVE LOGITS
    \
    2.63
    ING
    2.41
    謦
    2.38
    毟
    2.20
    )
    2.16
    ౧
    2.14
    ꯳
    2.11
    [
    2.11
    ᷆
    2.00
    ዡ
    1.97
    Activations Density 0.012%

    No Known Activations