© 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. 60289
    Prev
    Next
    INDEX
    Explanations

    ending or cancellation

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

    The neuron activates on words naming acts of removal or termination—e.g. dismissals, firings, evacuations, closures.

    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
    bereich
    -0.93
    нусы
    -0.90
     DAILY
    -0.85
     требует
    -0.84
    tian
    -0.83
    mények
    -0.82
    tacte
    -0.82
    vian
    -0.81
     모든
    -0.81
     Rolf
    -0.80
    POSITIVE LOGITS
     proceedings
    1.40
     notices
    1.22
     notice
    1.18
     procedure
    1.05
     decision
    1.05
     avven
    1.02
     of
    1.02
     process
    0.98
     notification
    0.97
     occurred
    0.97
    Activations Density 0.082%

    No Known Activations