© 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. 68247
    Prev
    Next
    INDEX
    Explanations

    specific names and titles

    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
     But
    -2.17
    などで
    -2.14
     أخرى
    -2.02
     can
    -1.88
    }
    -1.86
     behöver
    -1.82
     has
    -1.79
     znamená
    -1.76
    겁
    -1.75
     embodies
    -1.74
    POSITIVE LOGITS
    泐
    2.05
    每一次
    1.92
    の概要
    1.90
    ፳
    1.88
     exceedingly
    1.87
     amazingly
    1.83
     exceptionally
    1.82
     состояние
    1.80
    をチェック
    1.80
    丷
    1.77
    Activations Density 0.002%

    No Known Activations