© 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. 10537
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    The neuron strongly activates on past-tense speech-reporting verbs (e.g. said, asked, hissed, growled, responded, admitted).

    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
     (
    -1.89
     all
    -1.65
     J
    -1.50
     two
    -1.49
     H
    -1.45
     N
    -1.44
     E
    -1.38
     by
    -1.34
     K
    -1.33
     даже
    -1.32
    POSITIVE LOGITS
     konkrét
    1.53
    1.48
    娡
    1.41
     kroppen
    1.41
     uscita
    1.40
     varietà
    1.38
     vatten
    1.38
     singola
    1.38
    stateMutability
    1.37
     personalización
    1.36
    Activations Density 0.002%

    No Known Activations