© 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. 71642
    Prev
    Next
    INDEX
    Explanations

    product development

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

    The neuron fires on HTML/XML comment delimiters (i.e. “<!-- … -->”).

    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
    還是
    -1.53
     still
    -1.47
     españa
    -1.41
    镦
    -1.40
    #
    -1.33
     guerrero
    -1.30
    [
    -1.30
    \
    -1.27
     THIS
    -1.27
    zes
    -1.27
    POSITIVE LOGITS
     to
    1.66
    剮
    1.61
    huile
    1.52
    ܜ
    1.46
    ！(
    1.43
    inverno
    1.40
    \},
    1.32
    になりました
    1.30
     guter
    1.30
    incontro
    1.30
    Activations Density 0.001%

    No Known Activations