© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    Legal citations with names

    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
     as
    -1.87
     including
    -1.58
     first
    -1.52
     now
    -1.34
     his
    -1.27
     H
    -1.27
    </em>
    -1.24
     primeros
    -1.23
     Much
    -1.22
     primeras
    -1.22
    POSITIVE LOGITS
     épisode
    1.34
     aqueles
    1.27
     paru
    1.26
    
    1.25
    //
    1.25
    nellement
    1.22
    ¨
    1.20
    Kons
    1.20
    ension
    1.19
     soutenir
    1.18
    Activations Density 0.058%

    No Known Activations