© 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. 14300
    Prev
    Next
    INDEX
    Explanations

    class and interface definitions

    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
    <td>
    -0.96
    教会
    -0.95
    敷
    -0.92
    nikova
    -0.92
    church
    -0.90
    ?>">
    -0.90
     застосування
    -0.89
    ⃢
    -0.89
    чук
    -0.88
    ̀i
    -0.88
    POSITIVE LOGITS
    partes
    0.93
    ~$\
    0.93
     Entste
    0.90
     years
    0.89
     접
    0.88
    Especies
    0.88
    Trayectoria
    0.87
    Balas
    0.86
     могут
    0.85
     malattia
    0.85
    Activations Density 0.001%

    No Known Activations