© 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. 10-GEMMASCOPE-RES-131K
    7. 130208
    Prev
    Next
    INDEX
    Explanations

    belief and disbelief

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

    The neuron activates on words that express doubt or incredulity (e.g., “disbelief,” “incredulous,” “unbelievable,” “believe”).

    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
     $
    -1.71
     ihe
    -1.66
    Cevap
    -1.59
    嵙
    -1.54
    ㈪
    -1.52
     \\
    -1.50
    AdvEx
    -1.47
    proyecto
    -1.46
     jigsaw
    -1.46
     indict
    -1.42
    POSITIVE LOGITS
    .
    2.09
     ilumin
    1.74
     espal
    1.63
     industria
    1.60
     artesanal
    1.54
     churras
    1.52
     preliminar
    1.49
    {
    1.48
     capilar
    1.47
    取决
    1.46
    Activations Density 0.012%

    No Known Activations