© 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. 113564
    Prev
    Next
    INDEX
    Explanations

    commercial license or use

    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
     The
    -3.06
    ℟
    -2.97
    ЛИ
    -2.70
    不太
    -2.66
    cisive
    -2.59
     quando
    -2.58
    籥
    -2.55
    鵙
    -2.48
     伸
    -2.48
    を選ぶ
    -2.48
    POSITIVE LOGITS
    ization
    3.77
    𖥧
    3.02
     現貨
    2.86
    ции
    2.80
    uttgart
    2.75
    襤
    2.75
    ”，
    2.72
     That
    2.72
    ā
    2.64
    屜
    2.63
    Activations Density 0.011%

    No Known Activations