© 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. 6842
    Prev
    Next
    INDEX
    Explanations

    future events and announcements

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

    The neuron activates most strongly on words and phrases describing violent threats or apocalyptic violence (e.g. “wall of violence,” “violence,” “world”).

    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
     yesterday
    -1.07
    Yesterday
    -1.02
    คง
    -0.92
    报记者
    -0.86
     can
    -0.86
     you
    -0.85
     now
    -0.85
    Created
    -0.85
     tadi
    -0.85
    Istorija
    -0.85
    POSITIVE LOGITS
     spesielt
    1.22
     will
    1.15
     viendra
    1.07
     SOON
    1.01
     veldig
    1.00
     internetu
    0.98
     큰
    0.96
     coffers
    0.95
    ឹ
    0.93
     igjen
    0.92
    Activations Density 0.007%

    No Known Activations