© 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. 22-GEMMASCOPE-RES-131K
    7. 33934
    Prev
    Next
    INDEX
    Explanations

    government interference and factions

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

    The neuron strongly activates on named entities—proper names, acronyms, and organization or party labels.

    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
     especially
    -1.37
     chré
    -1.17
     /
    -1.16
     \
    -1.13
     گیاه
    -1.11
     ειδ
    -1.10
     erity
    -1.09
     τὸν
    -1.09
     vielleicht
    -1.09
     And
    -1.08
    POSITIVE LOGITS
    ּוֹ
    1.71
    וּ
    1.44
    ִּ
    1.33
    ceptable
    1.31
    ַּ
    1.20
     vakantie
    1.16
    breviations
    1.15
    Читать
    1.15
     RECOMMENDED
    1.14
     officio
    1.14
    Activations Density 0.044%

    No Known Activations