© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16092
    Prev
    Next
    INDEX
    Explanations

    Courses, Kits, Guides, Education, Analysis

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

    The neuron flags words and phrases that signal social or political issues—particularly terms around activism, injustice, and inequality.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muß
    1.30
    
    1.20
    いろいろ
    1.16
     problems
    1.12
     Problems
    1.11
     PROBLEMS
    1.10
     numai
    1.08
    
    1.08
    
    1.08
    problems
    1.06
    POSITIVE LOGITS
     impactful
    1.98
     reimag
    1.95
     metaverse
    1.80
     TikTok
    1.74
     onboarding
    1.65
     curated
    1.63
    TikTok
    1.62
     Metaverse
    1.59
     Canva
    1.55
     livestream
    1.54
    Activations Density 0.462%

    No Known Activations