© 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. 10-GEMMASCOPE-RES-131K
    7. 128310
    Prev
    Next
    INDEX
    Explanations

    Go code keywords

    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_10/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
     this
    -1.59
    ﻷ
    -1.47
    メラ
    -1.46
     семь
    -1.45
     its
    -1.45
     Schiffe
    -1.41
     Typen
    -1.34
     cremallera
    -1.33
    楽しかった
    -1.33
    ILERS
    -1.31
    POSITIVE LOGITS
     but
    2.94
     if
    2.45
     should
    1.82
     चुनें
    1.80
     если
    1.66
    如果
    1.65
     اگر
    1.64
    atric
    1.58
     pidió
    1.55
     dacă
    1.53
    Activations Density 0.023%

    No Known Activations