© 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. 59554
    Prev
    Next
    INDEX
    Explanations

    (at your option) license

    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
    鼻子
    -0.77
    matrix
    -0.74
    matt
    -0.71
    Matrices
    -0.71
    টি
    -0.71
     found
    -0.71
    xff
    -0.70
    NotFound
    -0.69
    тли
    -0.68
    unto
    -0.68
    POSITIVE LOGITS
     vẫn
    0.87
    핍
    0.85
    STILL
    0.82
    号線
    0.77
     dudes
    0.77
     contexts
    0.76
     Provider
    0.73
    conexao
    0.73
    Connection
    0.72
     Async
    0.72
    Activations Density 0.015%

    No Known Activations