© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65202
    Prev
    Next
    INDEX
    Explanations

    variable and type declarations

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

    The neuron fires on documentation‐style comment annotations (e.g. docblock stars “*”, at-tags “@…”, type names and numeric tags) 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_34/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
    函数
    -1.08
     parameters
    -0.93
     returning
    -0.89
    参数
    -0.88
     function
    -0.87
    ♡
    -0.87
    paramref
    -0.85
    返回
    -0.85
     함수
    -0.82
     уже
    -0.82
    POSITIVE LOGITS
    var
    1.37
     var
    1.09
     type
    1.05
    变量
    0.96
    ousands
    0.92
     variable
    0.91
     TYPE
    0.88
    varia
    0.87
    ℅
    0.87
     klokken
    0.86
    Activations Density 0.007%

    No Known Activations