© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39025
    Prev
    Next
    INDEX
    Explanations

    Mun followed by names and places

    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
     jedną
    -2.67
     факторов
    -2.42
     It
    -2.36
     harganya
    -2.28
    渽
    -2.25
    偌
    -2.23
     Aufenthal
    -2.22
     znacznie
    -2.20
    取り組
    -2.19
     know
    -2.17
    POSITIVE LOGITS
    1
    3.05
    虓
    2.89
    (
    2.78
    蚡
    2.70
    蟶
    2.64
     réjou
    2.48
    \
    2.45
    м
    2.41
    釓
    2.34
     préoccup
    2.31
    Activations Density 0.005%

    No Known Activations