© 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. 22-GEMMASCOPE-RES-131K
    7. 70478
    Prev
    Next
    INDEX
    Explanations

    domains and specialties

    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
     to
    -1.63
     only
    -1.62
     after
    -1.54
     verbringen
    -1.29
     without
    -1.24
     before
    -1.18
     may
    -1.15
    8
    -1.12
     that
    -1.11
    을
    -1.11
    POSITIVE LOGITS
     Romains
    1.39
    ADORES
    1.32
    ViewChild
    1.21
     notamment
    1.20
     abiye
    1.18
    方面
    1.17
     saab
    1.17
    āju
    1.16
     harita
    1.16
    zések
    1.16
    Activations Density 0.054%

    No Known Activations