© 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. 42401
    Prev
    Next
    INDEX
    Explanations

    as you may know

    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
     each
    -2.09
     both
    -1.74
     what
    -1.27
     daugiau
    -1.26
     every
    -1.26
     quieren
    -1.23
     чор
    -1.22
    al
    -1.20
     каждой
    -1.20
     specifically
    -1.19
    POSITIVE LOGITS
    ENIA
    1.48
     estreno
    1.48
     aident
    1.46
     malgré
    1.45
     semelh
    1.41
     durant
    1.35
     tráiler
    1.34
    Lastly
    1.34
     manières
    1.32
    razioni
    1.29
    Activations Density 0.047%

    No Known Activations