© 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. 44896
    Prev
    Next
    INDEX
    Explanations

    sum followed by parentheses

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

    This neuron detects calls to aggregate or reduction functions (e.g. sum(…), max(…), min(…), any(…)) in code.

    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
    を作成
    -1.49
    ”
    -1.49
    ▬▬▬▬▬▬▬▬
    -1.41
    “.
    -1.39
     Such
    -1.39
     adept
    -1.39
    ...”
    -1.36
    ”(
    -1.34
    ??)
    -1.33
    あった
    -1.32
    POSITIVE LOGITS
     colheres
    1.88
    8
    1.87
    6
    1.75
     it
    1.59
    大家都
    1.45
    5
    1.45
    3
    1.45
     then
    1.45
    我在
    1.43
    bảng
    1.42
    Activations Density 0.006%

    No Known Activations