© 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. 44829
    Prev
    Next
    INDEX
    Explanations

    Saskatoon Saskatchewan Albert

    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
    拶
    -1.40
    ዑ
    -1.36
    釙
    -1.35
    扃
    -1.35
    乆
    -1.32
    赁
    -1.30
    那里
    -1.29
    奩
    -1.28
     Для
    -1.28
     două
    -1.27
    POSITIVE LOGITS
     &
    1.48
    cellaneous
    1.46
     bahkan
    1.38
     Saskatchewan
    1.36
     addition
    1.36
     recomend
    1.30
     old
    1.27
     Italian
    1.26
     loud
    1.26
     depths
    1.23
    Activations Density 0.018%

    No Known Activations