© 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. 34-GEMMASCOPE-RES-131K
    7. 55769
    Prev
    Next
    INDEX
    Explanations

    code assignments and definitions

    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_34/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
     rafraî
    -1.40
     poë
    -1.39
     ™
    -1.39
     siè
    -1.38
     sommige
    -1.38
     jezt
    -1.34
     délais
    -1.34
     anunció
    -1.30
     セーター
    -1.30
     célè
    -1.29
    POSITIVE LOGITS
     (
    2.23
     this
    2.11
     in
    1.77
     ((
    1.65
     new
    1.61
     without
    1.60
     at
    1.58
     from
    1.56
     on
    1.52
     all
    1.48
    Activations Density 0.033%

    No Known Activations