© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43340
    Prev
    Next
    INDEX
    Explanations

    for good or doubt

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

    This neuron specializes in spotting idiomatic intensifiers that signal finality or certainty—phrases like “once and for all,” “for good,” and “beyond doubt.”

    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
    {
    -1.64
    \
    -1.57
    strona
    -1.38
     linho
    -1.36
     für
    -1.31
    赑
    -1.31
    says
    -1.28
     binnen
    -1.27
    productos
    -1.25
    Enlla
    -1.25
    POSITIVE LOGITS
     Aunque
    1.50
    diera
    1.47
    蠓
    1.46
    >();
    
    1.42
    isbury
    1.41
    naeus
    1.41
     "");
    
    1.41
    存于互联网档案馆
    1.37
     [{
    
    1.37
    @[+][
    1.36
    Activations Density 0.008%

    No Known Activations