© 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. 64683
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets

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

    The neuron detects numeric literals (integer constants) 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
     esos
    -0.92
     znám
    -0.87
     leurs
    -0.80
     钱
    -0.78
    dición
    -0.78
     آنجا
    -0.77
     تلك
    -0.76
    幾天
    -0.75
     백
    -0.75
     slap
    -0.75
    POSITIVE LOGITS
     $
    1.89
    self
    1.10
    =>$
    1.01
     our
    0.98
     this
    0.98
     своей
    0.98
    がこの
    0.96
     =$
    0.95
    ']=$
    0.94
     deste
    0.94
    Activations Density 0.016%

    No Known Activations