© 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. 22-GEMMASCOPE-RES-131K
    7. 130672
    Prev
    Next
    INDEX
    Explanations

    all or everything included

    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
     some
    -1.38
     a
    -1.37
     with
    -1.35
     certain
    -1.27
     an
    -1.25
     one
    -1.21
     tertentu
    -1.17
    บาง
    -1.13
     Certain
    -1.12
    有些
    -1.06
    POSITIVE LOGITS
     everything
    2.03
     모든
    1.92
     даже
    1.87
     всички
    1.85
    even
    1.79
     even
    1.79
     حتی
    1.74
    EVERY
    1.73
     تمامی
    1.71
     навіть
    1.70
    Activations Density 0.051%

    No Known Activations