© 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. 22-GEMMASCOPE-RES-131K
    7. 12891
    Prev
    Next
    INDEX
    Explanations

    former roles and entities

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

    The neuron activates on mentions of formal organizations or high‐level titles (e.g. NFL, Chiefs, Saints, Tesla, Inc., college professor, head [coach]).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    目前
    -1.34
    当前
    -1.17
    が届
    -1.09
    naments
    -1.02
     akurat
    -1.00
     différente
    -0.98
     zatím
    -0.98
    𝓙
    -0.96
    emplares
    -0.96
     currently
    -0.96
    POSITIVE LOGITS
     and
    1.32
     but
    1.29
     before
    1.26
     who
    1.11
     of
    1.00
     früher
    1.00
     director
    0.99
    before
    0.96
     when
    0.93
     عيد
    0.92
    Activations Density 0.051%

    No Known Activations