© 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. 40134
    Prev
    Next
    INDEX
    Explanations

    kinda way

    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
     logro
    -1.44
     akci
    -1.39
     cuento
    -1.36
    blusa
    -1.26
    изображение
    -1.26
     diskusi
    -1.25
     bolí
    -1.22
    источник
    -1.21
     equipaje
    -1.20
    viele
    -1.20
    POSITIVE LOGITS
     you
    1.63
     so
    1.39
     $
    1.20
    ."
    1.18
    </i>
    1.16
     [
    1.15
    </b>
    1.14
     because
    1.14
     now
    1.12
    </em>
    1.11
    Activations Density 0.058%

    No Known Activations