© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68453
    Prev
    Next
    INDEX
    Explanations

    blog posts and product reviews

    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
     after
    -1.30
     for
    -1.27
     all
    -1.23
    wigs
    -1.20
     three
    -1.20
     some
    -1.19
     any
    -1.17
     at
    -1.16
     two
    -1.16
     just
    -1.16
    POSITIVE LOGITS
    öra
    1.16
     insanely
    1.16
    ברת
    1.12
    loß
    1.10
     Gauteng
    1.09
     акции
    1.09
     geheim
    1.09
     plenti
    1.08
    
    1.05
    äter
    1.05
    Activations Density 0.007%

    No Known Activations