© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4185
    Prev
    Next
    INDEX
    Explanations

    people's names

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

    The neuron fires on metadata‐style tokens—dates, numbers, headings, bylines, punctuation and other tokens typical of titles and captions rather than running text.

    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
     голов
    -0.76
     appeals
    -0.75
     QU
    -0.75
    rute
    -0.73
    fm
    -0.72
    mainan
    -0.72
    inius
    -0.71
    明月
    -0.71
     specialists
    -0.70
    waltung
    -0.69
    POSITIVE LOGITS
    новение
    0.81
     reshape
    0.75
    情
    0.74
    accordion
    0.72
     Poin
    0.71
    سر
    0.70
    (),"
    0.69
     Expos
    0.69
    ())
    0.68
    Oral
    0.68
    Activations Density 0.128%

    No Known Activations