© 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. 10-GEMMASCOPE-RES-131K
    7. 69613
    Prev
    Next
    INDEX
    Explanations

    PWN

    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
    “
    -1.22
     and
    -1.20
     you
    -1.14
     already
    -1.11
    rosoft
    -1.10
     usually
    -1.09
     if
    -1.09
     enter
    -1.07
     class
    -1.06
     generalmente
    -1.02
    POSITIVE LOGITS
     сні
    1.27
     Гі
    1.27
     navigu
    1.27
    Примі
    1.25
    مقاله
    1.24
     amea
    1.23
    現在の
    1.23
     dénon
    1.22
    Lösung
    1.20
    Ahol
    1.20
    Activations Density 0.005%

    No Known Activations