© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58724
    Prev
    Next
    INDEX
    Explanations

    Kubernetes pod configurations and specs

    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
     XXIV
    -1.47
     XXVI
    -1.46
     regeringen
    -1.41
    {*}
    -1.38
     XXIII
    -1.38
     млн
    -1.38
     nevoie
    -1.36
    <td>
    -1.34
     XXII
    -1.32
    ématiques
    -1.30
    POSITIVE LOGITS
     
    1.36
     to
    1.34
     подключения
    1.28
     něj
    1.23
     ativos
    1.23
     všetky
    1.23
    ↵
    1.18
    ↵↵
    1.17
     while
    1.15
    Libros
    1.13
    Activations Density 0.010%

    No Known Activations