© 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. 34-GEMMASCOPE-RES-131K
    7. 107412
    Prev
    Next
    INDEX
    Explanations

    following `the` or `he`

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

    This neuron detects words that mark reported speech or communication acts—e.g. verbs like “told,” “asked,” “said,” and nouns like “response.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    hemp
    -1.13
     polskich
    -1.11
     Erfindung
    -1.05
    Pherson
    -1.05
    weeted
    -1.03
    =$_
    -1.03
     Professors
    -1.03
     Könige
    -1.03
     Schülerinnen
    -1.02
     a
    -1.02
    POSITIVE LOGITS
     the
    2.81
    这位
    2.23
    這位
    1.75
    该
    1.59
    該
    1.50
     he
    1.44
     guy
    1.34
     him
    1.23
     she
    1.20
     该
    1.19
    Activations Density 0.088%

    No Known Activations