© 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. 31406
    Prev
    Next
    INDEX
    Explanations

    Vascular smooth, expected behavior

    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
    呤
    -1.02
     Speisen
    -0.87
    Ꮳ
    -0.82
    seni
    -0.82
    NÍ
    -0.81
    めんなさい
    -0.81
    velocityY
    -0.79
    ERe
    -0.77
    ماية
    -0.77
    我们就
    -0.77
    POSITIVE LOGITS
     expected
    1.19
     Describe
    1.16
     Expected
    1.14
     <!--
    1.02
    Expected
    0.98
     describe
    0.97
    Describe
    0.95
     steps
    0.92
    <!--
    0.90
     environment
    0.86
    Activations Density 0.068%

    No Known Activations