© 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. 67430
    Prev
    Next
    INDEX
    Explanations

    affirming certainty or expressing doubt

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

    This neuron detects occurrences of “doubt” and its derivatives used to express certainty (e.g., doubtless, undoubtedly, no 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
    )=>{
    -1.83
    メニューは
    -1.77
    ⽼
    -1.76
    
    -1.73
     whatnot
    -1.71
    Vlast
    -1.70
    ebenarnya
    -1.69
    ruecos
    -1.68
    女
    -1.63
    Wszyst
    -1.60
    POSITIVE LOGITS
    “
    2.16
    >
    1.63
     genaue
    1.62
    This
    1.60
    Continue
    1.58
     numerosi
    1.58
    Already
    1.56
     règne
    1.55
     weiße
    1.55
     chêne
    1.54
    Activations Density 0.005%

    No Known Activations