© 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. 119638
    Prev
    Next
    INDEX
    Explanations

    nominee or nominees

    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
     \
    -2.80
    }_{
    -2.63
     $^{
    -2.48
    읭
    -2.47
    ());
    -2.45
     schließen
    -2.36
     $[
    -2.34
     mismas
    -2.30
    طبيق
    -2.28
     gdyż
    -2.28
    POSITIVE LOGITS
     علاج
    2.31
    勿論
    2.30
    ↵
    2.30
    なんだけど
    2.22
    '
    2.09
    "¿
    2.05
     放題
    2.02
     “
    2.02
     welchem
    1.98
    ebook
    1.96
    Activations Density 0.002%

    No Known Activations