© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69014
    Prev
    Next
    INDEX
    Explanations

    pedia archive

    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
     городского
    -1.86
    癀
    -1.82
    このように
    -1.72
    兖
    -1.71
     I
    -1.67
    決して
    -1.64
    襪
    -1.63
    }$_
    -1.57
     venezolano
    -1.56
    raujo
    -1.54
    POSITIVE LOGITS
     to
    2.14
    都是
    1.72
     mereka
    1.59
    0
    1.56
    ཫ
    1.56
     สอง
    1.46
    庒
    1.46
    囖
    1.45
    
    1.42
    gestellten
    1.41
    Activations Density 0.191%

    No Known Activations