© 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. 10-GEMMASCOPE-RES-131K
    7. 12505
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    -1.99
    providedIn
    -1.84
    -1.83
     در
    -1.77
     даже
    -1.67
     اگر
    -1.63
     حتی
    -1.61
     без
    -1.59
    -1.51
     если
    -1.49
    POSITIVE LOGITS
     about
    1.59
    饜
    1.58
    並んで
    1.52
    攵
    1.52
    髕
    1.48
     are
    1.48
     拡大
    1.46
     뉴스
    1.46
     and
    1.45
     gekozen
    1.45
    Activations Density 0.078%

    No Known Activations