© 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. 91295
    Prev
    Next
    INDEX
    Explanations

    organizers and 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
    っていない
    -0.80
    フジテレビ
    -0.80
     cancha
    -0.80
     اختلاف
    -0.79
    captcha
    -0.78
     semp
    -0.78
     поклон
    -0.77
     barcel
    -0.77
     edile
    -0.75
     cristian
    -0.75
    POSITIVE LOGITS
     organizer
    1.44
     organizers
    1.38
     Climate
    1.20
     Moms
    1.20
    organizer
    1.19
     Organizer
    1.19
     climate
    1.17
    organiser
    1.15
     #
    1.11
     Extinction
    1.11
    Activations Density 0.042%

    No Known Activations