© 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. 87010
    Prev
    Next
    INDEX
    Explanations

    petitions and signatures

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

    The neuron detects mentions of petitions or petition-signing campaigns.

    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
    perp
    -0.81
    entierung
    -0.81
    äge
    -0.79
    announced
    -0.79
     medan
    -0.79
     Scy
    -0.78
    Pal
    -0.77
    Male
    -0.75
    claimed
    -0.74
    sudo
    -0.74
    POSITIVE LOGITS
     petition
    3.55
     petitions
    2.78
     signatures
    2.58
     Petition
    2.48
    Petition
    2.44
    petition
    2.42
     PETITION
    2.38
    signatures
    2.17
     Signatures
    2.03
     petitioners
    1.99
    Activations Density 0.059%

    No Known Activations