© 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. 22-GEMMASCOPE-RES-131K
    7. 10848
    Prev
    Next
    INDEX
    Explanations

    Recommended Citation

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

    The neuron fires strongly on standalone uppercase section headings (e.g. “Reasons” or “Recommended”), i.e. document titles or major section 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_22/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
     in
    -1.78
     without
    -1.70
     became
    -1.63
     only
    -1.62
     begin
    -1.59
     began
    -1.58
     came
    -1.55
     started
    -1.47
     at
    -1.46
     made
    -1.46
    POSITIVE LOGITS
    あぁ
    1.57
    甗
    1.45
    possibly
    1.45
     REALLY
    1.41
    尤其
    1.41
    あー
    1.41
     probablement
    1.40
     miſ
    1.38
     parfois
    1.37
    ほんとに
    1.37
    Activations Density 0.000%

    No Known Activations