© 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. 66219
    Prev
    Next
    INDEX
    Explanations

    section headings or structured data

    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
     Vgl
    -0.88
     ДЛЯ
    -0.87
     ölüm
    -0.85
    Сы
    -0.85
     ujar
    -0.84
    Миха
    -0.83
     ДЕ
    -0.82
     ナイキ
    -0.81
     БЕ
    -0.79
    ȅ
    -0.78
    POSITIVE LOGITS
     Section
    1.00
    Section
    0.94
     appelé
    0.92
    appel
    0.87
    SECTION
    0.83
     cost
    0.82
    ISTRO
    0.82
    Odkazy
    0.81
     I
    0.79
     jouets
    0.79
    Activations Density 0.036%

    No Known Activations