© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77476
    Prev
    Next
    INDEX
    Explanations

    entity followed by connective words

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

    The neuron strongly activates on common, singular nouns (e.g. land, city, drug, question, place, movie, market, year).

    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
     включая
    -1.11
    最強
    -1.07
    ieties
    -1.02
     pagar
    -1.00
    titled
    -1.00
     الاحتلال
    -1.00
    がございます
    -0.99
    ഫ
    -0.99
    selves
    -0.97
    orithms
    -0.97
    POSITIVE LOGITS
     that
    3.50
     of
    3.41
     to
    2.56
     you
    2.39
     for
    2.36
     with
    1.80
     whose
    1.70
     we
    1.55
     everyone
    1.52
     worth
    1.51
    Activations Density 0.075%

    No Known Activations