© 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. 12601
    Prev
    Next
    INDEX
    Explanations

    titles and facts

    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
    Tujuan
    -1.26
    Před
    -1.25
    dyž
    -1.23
    čius
    -1.22
    笮
    -1.21
     PUSTAKA
    -1.20
     pozdě
    -1.19
    プリング
    -1.17
    5
    -1.16
    icône
    -1.15
    POSITIVE LOGITS
     or
    1.52
     our
    1.52
    いただけます
    1.38
     $-$
    1.38
     it
    1.30
     in
    1.28
     kämp
    1.27
     bekom
    1.23
    が悪い
    1.22
     still
    1.21
    Activations Density 0.022%

    No Known Activations