© 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. 22-GEMMASCOPE-RES-131K
    7. 34642
    Prev
    Next
    INDEX
    Explanations

    code or questions

    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
     last
    -1.02
     levantar
    -1.01
    βα
    -1.01
    ėte
    -0.99
    rentices
    -0.97
     höl
    -0.93
    bewerken
    -0.93
    leggio
    -0.93
    курс
    -0.93
    🚄
    -0.91
    POSITIVE LOGITS
     hewan
    1.06
     capables
    1.05
    Forrás
    1.05
     botines
    1.03
     AudioClip
    1.03
     őket
    1.02
    啻
    1.02
     of
    1.02
    Türkiye
    1.02
    definitely
    1.00
    Activations Density 0.008%

    No Known Activations