© 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. 32570
    Prev
    Next
    INDEX
    Explanations

    German federal or state entities

    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
    ustimmung
    -0.75
    Anno
    -0.71
     Anno
    -0.71
    Mitt
    -0.69
     boil
    -0.69
     hydropower
    -0.68
     boils
    -0.68
    Mall
    -0.67
    يي
    -0.67
    mall
    -0.66
    POSITIVE LOGITS
    urtstag
    0.84
    doPost
    0.80
     Chan
    0.73
     pelúcia
    0.73
    Startup
    0.72
    gex
    0.71
    ReadInt
    0.70
     competent
    0.70
    加载
    0.70
    allee
    0.69
    Activations Density 0.024%

    No Known Activations