© 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. 27261
    Prev
    Next
    INDEX
    Explanations

    restrictions and closures

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

    The neuron strongly activates on words naming imposed restrictions or stoppages—e.g. lockdown, shutdown, curfew, blackout, blockade, or sanctions.

    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
    </h3>
    -1.60
    Koordinaten
    -1.47
    鲞
    -1.38
    Udo
    -1.35
     приходит
    -1.33
    getNome
    -1.30
    Mvh
    -1.30
    %;">
    -1.29
     Udo
    -1.26
    zembro
    -1.23
    POSITIVE LOGITS
    ed
    1.34
    𓐍
    1.21
    みます
    1.17
    aktifkan
    1.13
    uruhan
    1.13
     restrictions
    1.13
    else
    1.11
    rália
    1.10
     instructions
    1.10
     for
    1.10
    Activations Density 0.008%

    No Known Activations