© 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. 34-GEMMASCOPE-RES-131K
    7. 62950
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

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

    The main thing this neuron does is detect the keyword “class” (e.g. class declarations or mentions of class in code and comments).

    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
     abenço
    -0.88
    anci
    -0.85
    יף
    -0.84
    Keen
    -0.81
    eaways
    -0.79
     survive
    -0.78
    AppendLine
    -0.78
     tež
    -0.77
    MediaStore
    -0.76
     esconder
    -0.76
    POSITIVE LOGITS
     {@
    0.88
    however
    0.88
    HttpSession
    0.87
     '{@
    0.87
     lunak
    0.83
    >{@
    0.83
     for
    0.82
    though
    0.81
    bangun
    0.78
    『
    0.77
    Activations Density 0.000%

    No Known Activations