© 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. 19587
    Prev
    Next
    INDEX
    Explanations

    theater, music, film, and wrestling

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

    The neuron is looking for prominent category nouns—especially names of professions, artistic forms, organizations, and similar domain‐specific activity titles.

    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
     its
    -1.38
    those
    -1.33
    particularly
    -1.30
     nieuwe
    -1.23
     already
    -1.17
     overly
    -1.14
    nowu
    -1.11
     zwłaszcza
    -1.11
     وض
    -1.09
     sekitarnya
    -1.09
    POSITIVE LOGITS
     from
    1.36
     There
    1.30
     Unlike
    1.28
    After
    1.28
     späteren
    1.27
    During
    1.27
     Eventually
    1.25
    После
    1.19
     Когда
    1.16
     möglichen
    1.15
    Activations Density 0.115%

    No Known Activations