© 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. 22-GEMMASCOPE-RES-131K
    7. 15618
    Prev
    Next
    INDEX
    Explanations

    programming language structure tokens

    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_22/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
    ּוֹ
    -2.30
     السياس
    -1.57
    ַּ
    -1.48
    ִּ
    -1.48
    ־ה
    -1.47
    ֶּ
    -1.45
    וּ
    -1.35
    וּ
    -1.21
    ֵּ
    -1.19
    bietern
    -1.19
    POSITIVE LOGITS
     ὁ
    1.76
    ׇ
    1.59
     ܐ
    1.59
     chré
    1.58
    juries
    1.52
     princesas
    1.50
     eccl
    1.49
     religieux
    1.48
     motocicletas
    1.44
     τὰ
    1.41
    Activations Density 0.043%

    No Known Activations