© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92368
    Prev
    Next
    INDEX
    Explanations

    License, suit, bubbles, anim, 浏览, Sunday, Q

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

    The neuron activates on programming‐language syntax tokens and keywords (e.g. “module,” “class,” “function,” “import,” comment delimiters), effectively detecting snippets of source 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
     WebDriverWait
    -0.84
     CharSequence
    -0.83
    جن
    -0.82
     datetime
    -0.82
     <<-
    -0.82
     llorando
    -0.81
     AppBundle
    -0.80
     KeyEvent
    -0.79
     मी
    -0.76
    ticed
    -0.75
    POSITIVE LOGITS
     tween
    0.89
     lobby
    0.85
    tween
    0.85
     egret
    0.79
    焚
    0.78
    理解
    0.77
     Turbul
    0.77
    有一个
    0.75
     Sprite
    0.75
     Nutri
    0.74
    Activations Density 0.004%

    No Known Activations