© 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. 9122
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

    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
    Ayrıca
    -1.18
     població
    -1.16
     Prospects
    -1.14
    částí
    -1.14
     också
    -1.14
     on
    -1.13
    ）、
    -1.10
     nozze
    -1.09
    ++,
    -1.08
     more
    -1.07
    POSITIVE LOGITS
     pudieran
    1.48
     reacties
    1.41
    しますね
    1.34
    tiously
    1.31
     resultan
    1.28
    了你
    1.27
    しますが
    1.25
    ਖ਼
    1.24
     andere
    1.24
     permitan
    1.23
    Activations Density 0.079%

    No Known Activations