© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11494
    Prev
    Next
    INDEX
    Explanations

    foreign language and common words

    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
     поскольку
    -1.08
     لذا
    -1.05
    смарт
    -1.05
     péché
    -1.03
     souvent
    -1.01
     sempre
    -1.01
    യ
    -1.01
     niektor
    -1.00
     "}";
    -1.00
     généralement
    -0.99
    POSITIVE LOGITS
     another
    1.43
     such
    1.22
     your
    1.19
    しかも
    1.18
     its
    1.18
    ものである
    1.09
     otra
    1.08
    toDouble
    1.07
     otro
    1.03
    ものです
    1.02
    Activations Density 0.077%

    No Known Activations