© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89762
    Prev
    Next
    INDEX
    Explanations

    category listings

    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
    庁
    -0.68
     לצ
    -0.66
    vie
    -0.65
     trabalhos
    -0.65
     Realistic
    -0.64
    ㋡
    -0.64
     ACCEPT
    -0.64
     accepting
    -0.63
    Realistic
    -0.63
     varsa
    -0.62
    POSITIVE LOGITS
    DDR
    0.71
    Teatro
    0.69
     發
    0.69
    Theater
    0.67
    Lup
    0.65
     pols
    0.65
    شت
    0.65
     zhu
    0.64
    調味料
    0.64
    Interv
    0.63
    Activations Density 0.083%

    No Known Activations