© 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. 99302
    Prev
    Next
    INDEX
    Explanations

    video or photo of

    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
    -1.37
     if
    -1.34
    媜
    -1.34
    Ⲉ
    -1.29
    蛸
    -1.26
    although
    -1.24
    lização
    -1.24
     byli
    -1.22
    へ行
    -1.20
     вечера
    -1.20
    POSITIVE LOGITS
    休闲
    1.30
     kürzlich
    1.26
    ブーツ
    1.23
    オフィス
    1.22
    
    1.20
    不錯
    1.18
     participates
    1.18
    㩒
    1.17
    ニット
    1.16
    别人的
    1.16
    Activations Density 0.037%

    No Known Activations