© 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. 41028
    Prev
    Next
    INDEX
    Explanations

    copyright in code headers

    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
     SOMETHING
    -1.34
     seront
    -1.26
     sécher
    -1.25
    IZONT
    -1.23
    ţion
    -1.22
     rojas
    -1.22
     DÍA
    -1.19
     شيء
    -1.17
     drzwi
    -1.17
    彡
    -1.16
    POSITIVE LOGITS
     to
    1.33
     is
    1.29
     quickly
    1.24
     its
    1.20
     until
    1.16
     несмотря
    1.16
     Until
    1.16
     with
    1.15
     only
    1.14
    </strong>
    1.13
    Activations Density 0.391%

    No Known Activations