© 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. 85286
    Prev
    Next
    INDEX
    Explanations

    official registers and lists

    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
    割と
    -2.33
    などなど
    -2.28
     gigantic
    -2.28
    就去
    -2.23
     largely
    -2.22
    "
    -2.20
     amazingly
    -2.19
    を中心
    -2.17
     mediocre
    -2.13
    コチラ
    -2.13
    POSITIVE LOGITS
    because
    2.55
    🎈
    2.28
    🌼
    2.19
    🅿
    2.16
    🔔
    2.16
    🌺
    2.14
    🎊
    2.14
    」
    2.11
    to
    2.06
    ｇ
    2.06
    Activations Density 0.013%

    No Known Activations