© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80815
    Prev
    Next
    INDEX
    Explanations

    java variable 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
     hecha
    -1.68
     أن
    -1.66
    GIUM
    -1.52
     sebagainya
    -1.41
    ONAUT
    -1.37
     теми
    -1.35
    ulaire
    -1.34
    спомина
    -1.34
    
    -1.34
     foarte
    -1.30
    POSITIVE LOGITS
    </h2>
    1.55
     beholder
    1.40
    lierten
    1.31
     deler
    1.30
     silla
    1.30
    자가
    1.28
     लोगों
    1.24
    ädigung
    1.23
     InputMaybe
    1.23
     lèvres
    1.23
    Activations Density 0.011%

    No Known Activations