© 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. 119817
    Prev
    Next
    INDEX
    Explanations

    dynasty names

    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
    慊
    -3.44
    ῎
    -3.39
    檍
    -3.38
    泂
    -3.27
    鹛
    -3.09
    鲧
    -3.08
     parachoque
    -3.05
    赑
    -3.05
    ᷆
    -3.02
    鑁
    -2.95
    POSITIVE LOGITS
    i
    4.31
    —
    3.61
    ’
    3.59
    c
    3.41
    &
    3.17
    I
    3.16
    A
    3.14
    </b>
    3.13
    [
    3.05
    .
    2.95
    Activations Density 0.003%

    No Known Activations