© 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. 35575
    Prev
    Next
    INDEX
    Explanations

    Hadrian's Wall Path

    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
     their
    -1.58
     this
    -1.55
     should
    -1.34
     of
    -1.28
     or
    -1.23
    )।
    -1.23
     these
    -1.20
     will
    -1.20
     you
    -1.19
     like
    -1.18
    POSITIVE LOGITS
     prevenção
    1.41
     correos
    1.34
    sometimes
    1.26
    Rè
    1.20
     áng
    1.20
     proteção
    1.19
    輅
    1.19
    骉
    1.18
     cuadrados
    1.18
     accesorios
    1.18
    Activations Density 0.000%

    No Known Activations