© 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. 103466
    Prev
    Next
    INDEX
    Explanations

    on after certain words

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

    The neuron is keyed to non-content metadata markers—things like “Comments Off,” “Forwarded by,” “From:,” and similar header/footer labels.

    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
     isInitialized
    -0.95
     liitty
    -0.85
     natomiast
    -0.77
     käyttää
    -0.77
     löyty
    -0.77
     kertoo
    -0.77
     pitä
    -0.77
     voidaan
    -0.74
    瑗
    -0.73
    voirs
    -0.73
    POSITIVE LOGITS
     on
    3.89
     trên
    2.78
     على
    2.61
     на
    2.42
     On
    2.38
    บน
    2.34
     på
    2.34
    On
    2.25
     על
    2.23
     روی
    2.14
    Activations Density 0.392%

    No Known Activations