© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98596
    Prev
    Next
    INDEX
    Explanations

    introductions to topics or entities

    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
     to
    -1.70
     its
    -1.57
     that
    -1.41
    скажите
    -1.28
     berdua
    -1.27
    bigr
    -1.24
     tersenyum
    -1.24
     leher
    -1.24
     mendengar
    -1.23
    شخص
    -1.22
    POSITIVE LOGITS
    </b>
    1.28
    ...
    1.23
    </h4>
    1.23
    </em>
    1.23
     protože
    1.23
     sonidos
    1.22
     duradero
    1.20
    a
    1.20
     hombros
    1.18
    ara
    1.17
    Activations Density 0.000%

    No Known Activations