© 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. 435
    Prev
    Next
    INDEX
    Explanations

    programming language imports

    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
     регионе
    -0.98
    ämie
    -0.97
     wife
    -0.97
    暁
    -0.93
     måneder
    -0.93
     senderismo
    -0.93
    🡪
    -0.93
     changed
    -0.92
     センター
    -0.92
    الثة
    -0.91
    POSITIVE LOGITS
     espirituales
    1.14
    ברים
    1.11
    sometimes
    1.05
     definiciones
    1.04
     teoría
    1.02
    rodu
    0.98
     a
    0.98
    ică
    0.98
    But
    0.95
     к
    0.94
    Activations Density 0.080%

    No Known Activations