© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104475
    Prev
    Next
    INDEX
    Explanations

    note that / keep in mind

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

    The neuron detects meta‐discourse cues and authorial pronouns—instances where the writer inserts personal remarks, clarifications, or “please note/keep in mind”-style commentary.

    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
     or
    -1.59
     begin
    -1.37
     of
    -1.34
     began
    -1.33
     shouldn
    -1.32
     Regardless
    -1.31
     should
    -1.29
     which
    -1.28
     Usually
    -1.26
     Shouldn
    -1.25
    POSITIVE LOGITS
     visites
    1.66
    potentially
    1.57
    appears
    1.56
    probably
    1.50
    despite
    1.48
    brought
    1.47
    might
    1.46
    helped
    1.45
    still
    1.44
    鈀
    1.43
    Activations Density 0.059%

    No Known Activations