© 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. 123945
    Prev
    Next
    INDEX
    Explanations

    waiting for the

    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
     showcases
    -1.59
     \
    -1.46
     celebrates
    -1.45
     همچنین
    -1.41
    ardez
    -1.38
    不但
    -1.36
    my
    -1.32
     satisfecho
    -1.32
    くれて
    -1.31
     wyświet
    -1.31
    POSITIVE LOGITS
    ⇨
    1.43
     betek
    1.41
     heilige
    1.33
    )<<
    1.32
    がない
    1.31
     Heilige
    1.27
     to
    1.26
    🛏
    1.23
     технологи
    1.23
    骓
    1.23
    Activations Density 0.014%

    No Known Activations