© 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. 10-GEMMASCOPE-RES-131K
    4. 1285
    Prev
    Next
    INDEX
    Explanations

    depends on factors

    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
     for
    -1.41
    是我的
    -1.32
     They
    -1.29
     alimente
    -1.26
     Lösungen
    -1.23
     piment
    -1.22
    спект
    -1.20
    ならば
    -1.17
    taciones
    -1.16
    一件
    -1.15
    POSITIVE LOGITS
     what
    1.34
     these
    1.33
     бъдат
    1.30
     those
    1.27
     huo
    1.26
     comenzará
    1.26
     soñar
    1.25
     that
    1.24
    خي
    1.22
     how
    1.18
    Activations Density 0.105%

    No Known Activations