© 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. 34-GEMMASCOPE-RES-131K
    7. 1935
    Prev
    Next
    INDEX
    Explanations

    messages and group discussions

    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
     принтом
    -0.81
    uckt
    -0.74
    ّ
    -0.74
    eras
    -0.73
     Bür
    -0.71
    而后
    -0.71
    ėtų
    -0.71
     Büro
    -0.70
     Bond
    -0.70
    编辑
    -0.69
    POSITIVE LOGITS
    Groups
    1.18
     GROUPS
    1.16
     groups
    1.13
     Groups
    1.12
    groups
    1.10
    GroupName
    1.03
    GROUPS
    1.02
     group
    0.95
    룹
    0.94
     группу
    0.93
    Activations Density 0.014%

    No Known Activations