© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14815
    Prev
    Next
    INDEX
    Explanations

    social issues and abstract concepts

    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_22/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
     gründ
    -1.09
     to
    -1.05
     näky
    -1.04
     ordinario
    -1.02
     beliebt
    -1.01
    um
    -0.98
    際に
    -0.96
    en
    -0.96
    un
    -0.95
    de
    -0.93
    POSITIVE LOGITS
    kjø
    1.11
     höl
    1.09
    komfort
    1.05
    lampa
    1.03
    naje
    1.01
    Tác
    1.01
    ถาม
    0.98
     OGSÅ
    0.98
    awarkan
    0.98
    rahat
    0.98
    Activations Density 0.099%

    No Known Activations