© 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. 9480
    Prev
    Next
    INDEX
    Explanations

    defining relations or comparisons

    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
     now
    -1.67
     also
    -1.52
    wanne
    -1.45
     still
    -1.43
     just
    -1.35
     herren
    -1.32
     important
    -1.32
     obviously
    -1.32
     specific
    -1.29
     relevant
    -1.26
    POSITIVE LOGITS
    一个是
    1.25
    (
    
    1.25
     vieler
    1.22
    Karakter
    1.21
    了一会儿
    1.20
     Zudem
    1.18
     guerras
    1.14
    鉀
    1.14
     både
    1.13
    استفاده
    1.13
    Activations Density 0.642%

    No Known Activations