© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12191
    Prev
    Next
    INDEX
    Explanations

    mathematical Roman font commands

    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
    ↵↵
    -3.61
    ↵
    -2.06
    -
    -2.05
    \_
    -1.88
    </sup>
    -1.88
    </h2>
    -1.84
    *
    -1.84
    ing
    -1.79
    ではまた
    -1.77
     rústico
    -1.76
    POSITIVE LOGITS
    噚
    2.03
    erintah
    1.96
    ПЕ
    1.86
    sipasi
    1.85
    xique
    1.81
     Zweiten
    1.80
     питання
    1.80
    :],
    1.79
     wanita
    1.78
    метры
    1.78
    Activations Density 0.006%

    No Known Activations