© 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. 36427
    Prev
    Next
    INDEX
    Explanations

    military / aviation

    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
    Törté
    -1.22
    ⬇
    -1.20
     煮
    -1.18
     inkább
    -1.18
     pinturas
    -1.11
    Если
    -1.11
    ９
    -1.11
     fön
    -1.10
     lät
    -1.09
    ТЕ
    -1.09
    POSITIVE LOGITS
     to
    1.34
     &
    1.32
     diversos
    1.21
     is
    1.13
     的
    1.09
    きち
    1.09
     diversas
    1.07
    d
    1.07
    "
    1.05
    &
    1.05
    Activations Density 0.134%

    No Known Activations