© 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. 23574
    Prev
    Next
    INDEX
    Explanations

    policy advice

    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
     microbiome
    -1.24
     LGBTQ
    -1.17
    https
    -1.16
     playbook
    -1.07
     kinda
    -1.07
     STEM
    -1.06
    upyter
    -1.05
     smartphone
    -1.03
    kede
    -1.02
     متعلقه
    -1.02
    POSITIVE LOGITS
     linkages
    1.25
    Eksterne
    1.02
     idéia
    1.02
    🙁
    1.02
     bocas
    1.02
     aceites
    1.02
     Apparently
    1.02
     Ironically
    1.01
     kuş
    1.01
     Millennium
    1.01
    Activations Density 0.041%

    No Known Activations