© 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. 22-GEMMASCOPE-RES-131K
    7. 15259
    Prev
    Next
    INDEX
    Explanations

    adverb of certainty or emphasis

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

    The neuron strongly responds to very common high-frequency English function words (e.g. pronouns, articles, prepositions) rather than content words.

    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
    EdgeInsets
    -1.29
     ebenso
    -1.21
    ּוֹ
    -1.16
     Cedex
    -1.15
     также
    -1.13
     Avez
    -1.13
    同比
    -1.11
    óta
    -1.09
     årets
    -1.09
     ebenfalls
    -1.08
    POSITIVE LOGITS
     probably
    1.50
     really
    1.41
     veldig
    1.40
     certainly
    1.36
     maybe
    1.36
     basically
    1.34
     definitely
    1.28
     veramente
    1.23
     väldigt
    1.21
     niega
    1.21
    Activations Density 0.006%

    No Known Activations