© 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. 10-GEMMASCOPE-RES-131K
    7. 58652
    Prev
    Next
    INDEX
    Explanations

    official bodies and regulations

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

    The neuron detects mentions of formal institutions, bodies, or official entities (e.g. commissions, agencies, centers, acts, orders, investigations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.28
     even
    -2.08
     bahkan
    -2.02
     даже
    -1.69
     not
    -1.64
     after
    -1.52
     out
    -1.52
     through
    -1.50
     from
    -1.49
     only
    -1.41
    POSITIVE LOGITS
    still
    1.49
     desempen
    1.44
    estimating
    1.40
     geralmente
    1.34
    recently
    1.27
     trabalha
    1.26
    commonly
    1.25
     perfecte
    1.24
     promove
    1.23
     serão
    1.22
    Activations Density 0.238%

    No Known Activations