© 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. 26021
    Prev
    Next
    INDEX
    Explanations

    last element

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

    The neuron fires whenever it sees HTML/JSX tag names or attribute names (e.g. li, a, href, role, class, data-*, ToggleButton, etc.).

    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
    UTO
    -0.85
     segundo
    -0.84
    🤳
    -0.78
    ucción
    -0.78
     transporta
    -0.77
    妤
    -0.77
    ństw
    -0.77
    šia
    -0.77
     kohdetta
    -0.77
    <0xB2>
    -0.76
    POSITIVE LOGITS
     last
    3.16
    最后
    2.55
     final
    2.50
     terakhir
    2.44
     lastly
    2.42
    Lastly
    2.41
    最後に
    2.33
    最後
    2.28
    last
    2.19
     Lastly
    2.16
    Activations Density 0.006%

    No Known Activations