© 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. 31073
    Prev
    Next
    INDEX
    Explanations

    key-value assignments or coded attributes

    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
     gjør
    -0.84
    นอก
    -0.82
     lenker
    -0.81
    ₩
    -0.81
    にします
    -0.81
    tadır
    -0.81
     Hä
    -0.80
    każ
    -0.80
    чни
    -0.79
     precies
    -0.79
    POSITIVE LOGITS
     "
    1.18
    %">
    1.04
     даже
    1.04
     навіть
    1.03
    even
    0.98
     跳转至
    0.94
    示例
    0.94
     “
    0.93
    ஞ
    0.93
    𝐆
    0.93
    Activations Density 0.018%

    No Known Activations