© 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. 10449
    Prev
    Next
    INDEX
    Explanations

    verbs of speaking followed by reported speech

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

    The neuron detects quote-attribution verbs (e.g. said, says, insisted, revealed, urged) that introduce or report speech.

    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
     There
    -1.94
     It
    -1.73
    ↵↵
    -1.71
    -1.50
     A
    -1.47
     That
    -1.45
    }
    -1.44
     Before
    -1.42
     After
    -1.38
     What
    -1.36
    POSITIVE LOGITS
     triko
    1.79
     parfü
    1.73
    袛
    1.63
     osta
    1.63
     gerai
    1.61
     dovr
    1.60
     akku
    1.60
     maksi
    1.60
     adatto
    1.59
     lauk
    1.59
    Activations Density 0.047%
    No Known Activations