© 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. 72448
    Prev
    Next
    INDEX
    Explanations

    votes and approvals

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

    This neuron detects mentions of legislative voting results, such as vote counts and abstentions.

    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
     already
    -1.14
     we
    -1.13
     things
    -1.09
     activities
    -1.07
     Informações
    -1.04
    vegli
    -1.04
     events
    -0.98
     Betrag
    -0.98
    ?
    -0.96
     Comunicação
    -0.95
    POSITIVE LOGITS
    INATION
    1.21
     étages
    1.12
    ּוֹ
    1.12
     различни
    1.07
    owulf
    1.07
     eenig
    1.07
     verschiedener
    1.04
    bolistas
    1.04
    issent
    1.04
     unſ
    1.02
    Activations Density 0.011%

    No Known Activations