© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7405
    Prev
    Next
    INDEX
    Explanations

    Chester

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

    The neuron fires on the first token of a new section or list item—e.g. numerals or words that head titles, headings, or list entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ية
    -2.78
    荅
    -2.77
    媖
    -2.66
    to
    -2.61
     ответить
    -2.45
     furthermore
    -2.45
    al
    -2.44
     proactively
    -2.44
    0
    -2.42
    要
    -2.42
    POSITIVE LOGITS
    {
    3.25
    乆
    3.02
     $^{\
    2.72
    VIATIONS
    2.56
     Our
    2.52
     distritos
    2.44
     was
    2.38
    旻
    2.34
    wakili
    2.33
    是这样
    2.31
    Activations Density 0.000%

    No Known Activations