© 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. 22-GEMMASCOPE-RES-131K
    7. 27429
    Prev
    Next
    INDEX
    Explanations

    dialogue speaker turn transitions

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

    The neuron flags tokens that begin a new sentence or dialogue line—i.e. sentence-initial 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
     ortaya
    -0.89
    ậm
    -0.84
    액
    -0.82
    koff
    -0.81
    Heath
    -0.80
    CONVERT
    -0.80
    Thailand
    -0.78
     Connect
    -0.78
    gbarkeit
    -0.77
     altijd
    -0.77
    POSITIVE LOGITS
     then
    2.02
    Then
    1.26
    then
    1.05
     Then
    1.02
    就开始
    0.95
     entonces
    0.94
     далее
    0.91
     further
    0.88
     allora
    0.88
    <>
    0.88
    Activations Density 0.010%

    No Known Activations