© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130301
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the word “without,” marking instances of that specific token in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    without

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    는데
    -1.18
    おすすめの
    -1.15
     also
    -0.94
    سوال
    -0.94
    %\[
    -0.93
     haces
    -0.91
    というのも
    -0.89
    楽しめます
    -0.88
    一辆
    -0.87
     areas
    -0.87
    POSITIVE LOGITS
     directly
    1.21
    必须
    1.15
     directement
    1.11
    直接
    1.09
     require
    1.08
    physical
    1.07
     葉
    1.04
     necessariamente
    1.04
     costly
    1.04
    需要
    1.04
    Activations Density 0.117%

    No Known Activations