© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29043
    Prev
    Next
    INDEX
    Explanations

    legislative actions and outcomes

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

    The neuron fires on mentions of legislative or congressional actions that include specific numeric figures.

    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
    3
    -1.36
     in
    -1.27
     at
    -1.26
    5
    -1.21
     wenden
    -1.19
     nové
    -1.18
    7
    -1.17
     of
    -1.14
    8
    -1.14
     can
    -1.13
    POSITIVE LOGITS
     bancada
    1.30
     movimenti
    1.23
    itzung
    1.21
    ↵↵
    1.20
     内衣
    1.18
     caratteri
    1.17
     messaggi
    1.16
     confronti
    1.16
     sintomi
    1.16
    cables
    1.14
    Activations Density 0.087%

    No Known Activations