© 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. 118512
    Prev
    Next
    INDEX
    Explanations

    license text and code constructs

    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
     pesquisa
    -0.73
     Tras
    -0.70
    vors
    -0.70
     sínt
    -0.68
     vícti
    -0.68
    ErrorMsg
    -0.68
    dirname
    -0.67
     boc
    -0.66
    ämme
    -0.66
     operasi
    -0.66
    POSITIVE LOGITS
     Terri
    0.96
    Unable
    0.91
    体
    0.83
     typeof
    0.79
     Liberal
    0.79
    <0x95>
    0.79
    ు
    0.75
    typeof
    0.75
    独
    0.73
    ő
    0.73
    Activations Density 0.428%

    No Known Activations