© 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. 75943
    Prev
    Next
    INDEX
    Explanations

    must reproduce this

    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
    깬
    -0.76
     xóa
    -0.75
    
    -0.69
    非
    -0.68
    izing
    -0.68
     残
    -0.68
    湘南
    -0.67
    detta
    -0.65
     lọc
    -0.65
     Erklärung
    -0.64
    POSITIVE LOGITS
    getAction
    0.81
     Hydro
    0.80
    ToAction
    0.72
     anla
    0.71
    queryset
    0.71
     장
    0.70
     wasm
    0.68
     science
    0.67
    ولة
    0.66
    avatars
    0.66
    Activations Density 0.072%

    No Known Activations