© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65907
    Prev
    Next
    INDEX
    Explanations

    climate change activists

    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_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
     ammunition
    -0.87
     positivity
    -0.76
    tosis
    -0.74
     */,
    -0.74
     rod
    -0.73
     gossip
    -0.70
    枪
    -0.70
     guns
    -0.70
     smokers
    -0.70
     misuse
    -0.69
    POSITIVE LOGITS
     Extinction
    1.13
     activists
    1.09
     protester
    1.06
     Climate
    0.98
     climate
    0.98
     Greenpeace
    0.93
     activist
    0.93
     protest
    0.91
    Climate
    0.91
    climate
    0.88
    Activations Density 0.013%

    No Known Activations