© 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. 103199
    Prev
    Next
    INDEX
    Explanations

    ServerTimestamp

    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
    룬
    -0.92
    addField
    -0.80
     manuf
    -0.77
    ᴳ
    -0.76
    rhino
    -0.75
    ۩
    -0.75
    inkler
    -0.73
     赛
    -0.72
     luxo
    -0.71
    yendo
    -0.71
    POSITIVE LOGITS
     Chairperson
    0.79
     currents
    0.73
     diaries
    0.73
    짤
    0.72
     nocy
    0.71
     HLA
    0.71
     events
    0.71
    caf
    0.69
     sentirse
    0.69
    FI
    0.68
    Activations Density 0.015%

    No Known Activations