© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106669
    Prev
    Next
    INDEX
    Explanations

    live performances

    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
    本书
    -0.86
     bolí
    -0.83
    녀
    -0.82
    Southwest
    -0.81
    Typically
    -0.79
    Truly
    -0.79
    Though
    -0.78
    ㅇ
    -0.78
    riman
    -0.77
    باء
    -0.77
    POSITIVE LOGITS
     khong
    0.86
     joked
    0.82
     oy
    0.81
     oídos
    0.81
    cektir
    0.79
    Concentr
    0.79
     Millionaire
    0.79
     assists
    0.78
     hyg
    0.78
     Romains
    0.78
    Activations Density 0.000%

    No Known Activations