© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    we as a group/organization

    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
     in
    -1.63
     is
    -1.25
    欵
    -1.25
     jeder
    -1.25
    ictwo
    -1.20
    athed
    -1.19
    ........
    -1.17
    寥
    -1.16
    setNome
    -1.14
    是我的
    -1.13
    POSITIVE LOGITS
     Люди
    1.32
     voltak
    1.27
    阵法
    1.23
     angustia
    1.22
    issipp
    1.22
    gorov
    1.20
    ochem
    1.16
     كما
    1.16
    “,
    1.16
     ͡
    1.16
    Activations Density 0.017%

    No Known Activations