© 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. 34-GEMMASCOPE-RES-131K
    7. 77454
    Prev
    Next
    INDEX
    Explanations

    languages and localization data

    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_34/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
     Tasmania
    -0.80
     isoto
    -0.75
    西藏
    -0.74
    الیا
    -0.73
    新疆
    -0.71
     Sicily
    -0.71
    thy
    -0.69
    试管
    -0.69
     Palestina
    -0.68
    pring
    -0.67
    POSITIVE LOGITS
     English
    4.28
     Spanish
    3.53
     French
    3.31
    English
    3.30
     German
    3.16
     Hindi
    3.00
     Arabic
    2.97
     english
    2.94
    中文
    2.81
     Portuguese
    2.80
    Activations Density 0.491%

    No Known Activations