© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70011
    Prev
    Next
    INDEX
    Explanations

    tell application

    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
     there
    -1.27
    梦见
    -1.23
    ”
    -1.20
    ’
    -1.19
    ющие
    -1.18
     tecnologias
    -1.17
     иной
    -1.16
     instituições
    -1.12
    ”、“
    -1.12
     muitos
    -1.12
    POSITIVE LOGITS
    película
    1.37
     '+':
    1.31
     Tüm
    1.31
    是怎么回事
    1.29
     Daß
    1.29
    都没
    1.27
     erläut
    1.23
    すでに
    1.23
    显然
    1.22
    既に
    1.20
    Activations Density 0.061%

    No Known Activations