© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20064
    Prev
    Next
    INDEX
    Explanations

    specific addition project

    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
    <bos>
    -2.28
     lucru
    -1.80
     evenement
    -1.78
    もあった
    -1.75
     alfo
    -1.58
    钏
    -1.55
    ichtete
    -1.53
    ⸢
    -1.52
    ichteten
    -1.52
    甞
    -1.48
    POSITIVE LOGITS
    別の
    2.11
    他の
    2.05
     for
    1.92
     with
    1.77
    Again
    1.70
     if
    1.66
     from
    1.54
    全部
    1.52
     plena
    1.51
    Lastly
    1.50
    Activations Density 0.034%

    No Known Activations