© 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. 128911
    Prev
    Next
    INDEX
    Explanations

    The neuron is picking out prominent action verbs—especially ones denoting communication or framing (e.g. shared, reported, denounced, condemned, politicized).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    political news and commentary

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ',
    -1.18
    Câ
    -1.13
    dicionado
    -1.10
     sometimes
    -1.09
    有害
    -1.08
    ánicos
    -1.07
     you
    -1.03
     projects
    -1.02
     boundaries
    -1.01
    巅峰
    -1.01
    POSITIVE LOGITS
     the
    1.63
     recent
    1.41
     étr
    1.33
     siè
    1.16
     news
    1.14
    ptăm
    1.06
     капю
    1.03
     réjou
    1.00
     âme
    1.00
     Friday
    1.00
    Activations Density 0.109%

    No Known Activations