© 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. 40221
    Prev
    Next
    INDEX
    Explanations

    it is likely that

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

    The neuron fires on hedge or modal adverbs expressing likelihood or uncertainty (e.g. “likely,” “unlikely,” “probable”).

    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
    фов
    -1.67
    亘
    -1.63
    ᐠ
    -1.58
    Ⅱ
    -1.55
    section
    -1.54
     misterioso
    -1.51
    atchewan
    -1.51
     circumvent
    -1.48
    риях
    -1.48
    乄
    -1.48
    POSITIVE LOGITS
     that
    2.56
    {
    2.00
    +
    1.71
     będziemy
    1.70
     any
    1.63
    (*´
    1.57
    =
    1.55
    >
    1.53
    にほんブログ村
    1.52
    2
    1.49
    Activations Density 0.013%

    No Known Activations