© 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. 90601
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    The neuron detects reporting or quotation attribution phrases—e.g., speaker names followed by verbs like “said,” “states,” “complained,” and the surrounding interview/quote context.

    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
     in
    -1.45
     here
    -1.25
     unserem
    -1.17
     nella
    -1.16
     हमारे
    -1.14
    ntesis
    -1.13
     there
    -1.11
    ｉ
    -1.09
     الأولى
    -1.09
     Another
    -1.09
    POSITIVE LOGITS
    つも
    1.32
    cillary
    1.20
     recently
    1.19
     frequ
    1.16
     şey
    1.10
    .
    1.09
    masyarakat
    1.02
    sebagai
    1.00
    血压
    1.00
     things
    0.98
    Activations Density 0.086%

    No Known Activations