© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117860
    Prev
    Next
    INDEX
    Explanations

    business alliances and members

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

    The neuron strongly activates on numeric tokens and punctuation used to mark dates, times, and dateline codes in news‐style 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
    getPort
    -0.77
    "/></
    -0.73
     commissioned
    -0.73
    ㎠
    -0.71
    Sh
    -0.71
    mainan
    -0.71
    krishna
    -0.71
     private
    -0.69
    راض
    -0.67
     derivative
    -0.66
    POSITIVE LOGITS
     alliance
    1.41
    alliance
    1.22
     Alliance
    1.18
    Alliance
    1.11
     alliances
    1.05
    联盟
    0.99
    member
    0.97
     afili
    0.97
     member
    0.95
     correspondents
    0.93
    Activations Density 0.031%

    No Known Activations