© 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. 28447
    Prev
    Next
    INDEX
    Explanations

    without followed by a qualifier

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

    The neuron specifically detects occurrences of the word “without.”

    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
    や
    -1.66
    は
    -1.37
    も
    -1.33
     not
    -1.27
     only
    -1.26
    を
    -1.23
     vitrine
    -1.23
    <bos>
    -1.23
    と
    -1.23
    と思って
    -1.20
    POSITIVE LOGITS
    為に
    1.94
    んですよ
    1.82
    んですよね
    1.68
    ほうがいい
    1.63
    にならない
    1.60
    様な
    1.55
    感じが
    1.54
    corrhi
    1.52
    
    1.52
    ようになりました
    1.51
    Activations Density 0.037%

    No Known Activations