© 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. 105390
    Prev
    Next
    INDEX
    Explanations

    American football defensive positions

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

    The neuron spikes on mentions of American football defensive positions and roles (e.g. linebacker, defensive end, special teams, safety).

    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
    》,
    -1.38
    "$_
    -1.27
     essenciais
    -1.26
    一個
    -1.25
     nacionales
    -1.23
    #
    -1.20
     informace
    -1.18
     pessoais
    -1.18
     rusa
    -1.17
     informací
    -1.17
    POSITIVE LOGITS
     you
    1.45
    ukary
    1.29
     lekko
    1.23
    ượu
    1.14
     unrelated
    1.13
     notare
    1.13
    ógicos
    1.13
     didn
    1.13
     So
    1.13
    ITATION
    1.12
    Activations Density 0.018%

    No Known Activations