© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71942
    Prev
    Next
    INDEX
    Explanations

    official government actions and events

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

    The neuron strongly activates on named entities—proper names, official titles, organizations, and dates—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_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
     sıcak
    -0.98
     alue
    -0.82
     νέ
    -0.82
    邉
    -0.82
    ømme
    -0.81
     kõik
    -0.81
     latter
    -0.80
    garanti
    -0.79
    孩子的
    -0.79
     entire
    -0.79
    POSITIVE LOGITS
    かし
    1.01
    żeli
    0.96
     also
    0.93
    жении
    0.88
     Montreal
    0.88
    例えば
    0.84
    Flav
    0.81
    衛隊
    0.79
    ：……
    0.79
     Langen
    0.78
    Activations Density 0.089%

    No Known Activations