© 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. 9087
    Prev
    Next
    INDEX
    Explanations

    nuclear weaponry and reading nooks

    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
    .”
    -2.34
    </h3>
    -2.33
    ꯵
    -2.22
    ⢌
    -2.17
    最初
    -2.17
    lossians
    -2.17
    s
    -2.09
    “.
    -2.03
     که
    -2.03
     gets
    -2.03
    POSITIVE LOGITS
    ਃ
    2.75
     décrit
    2.53
    籥
    2.45
    一旁
    2.41
    是啊
    2.31
    臜
    2.31
     The
    2.19
     acht
    2.14
     explicó
    2.11
    </b>
    2.05
    Activations Density 0.004%

    No Known Activations