© 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. 130473
    Prev
    Next
    INDEX
    Explanations

    sentence structure punctuation

    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
     fluxo
    -1.23
     fija
    -1.19
    変わらない
    -1.13
     donde
    -1.13
     notwendi
    -1.12
    回来了
    -1.11
     mueve
    -1.11
     podrá
    -1.11
     geprüft
    -1.09
     eixo
    -1.09
    POSITIVE LOGITS
     by
    1.27
    包括
    1.21
     when
    1.21
    在我们
    1.13
     those
    1.13
     Every
    1.11
     började
    1.07
     if
    1.05
     ensuring
    1.05
    تعداد
    1.04
    Activations Density 0.140%

    No Known Activations