© 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. 12120
    Prev
    Next
    INDEX
    Explanations

    monastery, paths, fastened

    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
    宬
    -2.45
    鯪
    -2.44
    饪
    -2.42
     traditionelle
    -2.39
     frança
    -2.28
     sains
    -2.28
    杁
    -2.28
     uſed
    -2.20
    ейчас
    -2.20
     multiuso
    -2.19
    POSITIVE LOGITS
    \
    2.55
    )$
    2.47
    ↵
    2.42
    c
    2.39
    ”
    2.34
    ”.
    2.34
     ६
    2.30
    ↵↵
    2.28
     o
    2.22
    ).
    2.22
    Activations Density 0.001%

    No Known Activations