© 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. 34-GEMMASCOPE-RES-131K
    7. 107463
    Prev
    Next
    INDEX
    Explanations

    legislative assembly or branch news

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

    The neuron fires on stems of words relating to legislative bodies or processes (e.g. “legislators,” “legislation,” “legislative,” “assembly”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ㉗
    -0.98
     literals
    -0.98
    的吧
    -0.96
     Substantial
    -0.90
    THEORY
    -0.88
     Crimean
    -0.88
     policiales
    -0.88
    PhysRev
    -0.88
     Möbel
    -0.86
    mawia
    -0.86
    POSITIVE LOGITS
    готовка
    1.06
    ative
    0.99
    коно
    0.99
     Branch
    0.94
    Assembly
    0.91
     montado
    0.90
     BRANCH
    0.90
    lative
    0.90
    Branch
    0.89
    тори
    0.89
    Activations Density 0.009%

    No Known Activations