© 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. 39861
    Prev
    Next
    INDEX
    Explanations

    Queen, coat, Jul, dialogue

    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
     diesem
    -1.53
     this
    -1.53
     that
    -1.32
     unserem
    -1.27
     =
    -1.27
    P
    -1.23
     often
    -1.22
     also
    -1.19
     ".
    -1.19
     our
    -1.17
    POSITIVE LOGITS
    Technologie
    1.27
    Recept
    1.18
    Katalog
    1.17
    Kontak
    1.16
     kabát
    1.12
    Reak
    1.12
    outros
    1.12
    Musique
    1.11
    Haut
    1.11
    Ingredi
    1.11
    Activations Density 0.001%

    No Known Activations