© 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. 110929
    Prev
    Next
    INDEX
    Explanations

    convene, convened, Rovers, Kanye

    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
     \
    -2.69
    }
    -2.59
     $
    -2.59
    2
    -2.41
     {
    -2.38
     worin
    -2.27
     womit
    -2.22
     zumal
    -2.14
    3
    -2.13
    C
    -2.09
    POSITIVE LOGITS
    </sup>
    2.89
    韞
    2.50
    嗵
    2.47
    浤
    2.31
    賅
    2.30
     Those
    2.22
    贽
    2.19
     nestled
    2.13
    豋
    2.13
    Подготовка
    2.11
    Activations Density 0.002%

    No Known Activations