© 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. 65661
    Prev
    Next
    INDEX
    Explanations

    Nathan Gregory

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

    The neuron strongly activates on edition/version markers—especially “4 E” (and related tokens like “&” in “D&D 4 E”) indicating references to the 4th edition.

    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
    oficial
    -0.76
     enseignants
    -0.73
    スムーズ
    -0.72
     maternelle
    -0.71
    guien
    -0.71
    decap
    -0.71
    Avoiding
    -0.71
    悸
    -0.71
    threading
    -0.70
    phrodite
    -0.69
    POSITIVE LOGITS
     encounter
    0.90
     until
    0.82
     Utility
    0.80
     Slides
    0.79
    slide
    0.76
     marked
    0.76
    hwnd
    0.75
     Binder
    0.74
    MoveNext
    0.73
     ongoing
    0.72
    Activations Density 0.015%

    No Known Activations