© 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. 10-GEMMASCOPE-RES-131K
    7. 101960
    Prev
    Next
    INDEX
    Explanations

    list items or sequences

    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_10/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
     宝
    -1.35
     reddish
    -1.31
    certain
    -1.30
    了两
    -1.29
     voit
    -1.27
     XVI
    -1.27
     большого
    -1.27
     моего
    -1.23
     THAN
    -1.22
     Ε
    -1.21
    POSITIVE LOGITS
     increased
    1.34
     are
    1.30
     notare
    1.26
     löyty
    1.25
     termica
    1.24
     обеспечивает
    1.23
     including
    1.22
     firmar
    1.20
     diverso
    1.20
     increases
    1.19
    Activations Density 0.125%

    No Known Activations