© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94004
    Prev
    Next
    INDEX
    Explanations

    copyright and license

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

    The neuron fires on comment‐block separator lines—i.e. sequences of repeated punctuation (asterisks, slashes, dashes) used to mark off or decorate code 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
    DTD
    -0.76
    RQ
    -0.76
     Mih
    -0.74
    inol
    -0.69
    aty
    -0.69
    پی
    -0.68
     unsus
    -0.67
    voltaic
    -0.66
    cierge
    -0.65
     Coffe
    -0.65
    POSITIVE LOGITS
    ското
    0.79
     dış
    0.75
    Amended
    0.71
    负责人
    0.70
     體
    0.70
    breakers
    0.69
     Commissioner
    0.68
    Commissioner
    0.67
     tone
    0.67
     disciplina
    0.66
    Activations Density 0.076%

    No Known Activations