© 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. 25640
    Prev
    Next
    INDEX
    Explanations

    reported speech and announcements

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

    The neuron fires most strongly on location names in news‐style datelines (e.g. “in Ado Ekiti”) and on section headings, effectively spotting place names used to introduce a quote or report.

    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
    vorous
    -0.88
    ([
    -0.85
    asily
    -0.84
     INTEGR
    -0.82
     Normandie
    -0.82
    angerschaft
    -0.81
    alers
    -0.80
    }$)
    -0.80
    liable
    -0.79
    circled
    -0.79
    POSITIVE LOGITS
     represented
    1.36
     earlier
    1.10
     keynote
    1.09
     while
    1.05
     later
    1.03
     speech
    1.02
     also
    0.99
     guests
    0.99
     Earlier
    0.98
     rappresent
    0.97
    Activations Density 0.002%

    No Known Activations