© 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. 39924
    Prev
    Next
    INDEX
    Explanations

    adding items to lists

    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
     that
    -1.65
     takı
    -1.30
    Both
    -1.16
    Either
    -1.13
    ceptable
    -1.13
     nagu
    -1.11
     especta
    -1.07
     ronda
    -1.06
    ्रीन
    -1.05
    📒
    -1.05
    POSITIVE LOGITS
     also
    2.03
     then
    1.21
     همچنین
    1.14
     natürlich
    1.12
     further
    1.10
     natomiast
    1.05
    还有
    1.05
    ats
    1.02
     також
    1.01
    ka
    0.99
    Activations Density 0.003%

    No Known Activations