© 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. 108224
    Prev
    Next
    INDEX
    Explanations

    numbers followed by mile

    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
    actéristiques
    -0.85
    齁
    -0.82
    SafeArea
    -0.81
    Libros
    -0.78
    などを
    -0.77
    Revenir
    -0.77
     ざ
    -0.76
    zapatos
    -0.75
    CLES
    -0.73
    送给
    -0.73
    POSITIVE LOGITS
     Mile
    1.66
    Mile
    1.44
    mile
    1.30
     mile
    1.25
     MILE
    1.10
    Degree
    0.81
    Zero
    0.79
     Four
    0.77
    Change
    0.77
     Degree
    0.76
    Activations Density 0.031%

    No Known Activations