© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43308
    Prev
    Next
    INDEX
    Explanations

    mechanical, luminous, entrusted

    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
    {
    -2.73
    }$
    -2.63
    栳
    -2.55
    l
    -2.52
    嘖
    -2.48
    </h1>
    -2.41
     then
    -2.38
     we
    -2.36
     aching
    -2.23
    </sub>
    -2.20
    POSITIVE LOGITS
    s
    2.53
    ttino
    2.38
    趼
    2.34
    一部分
    2.33
    新的
    2.27
    侂
    2.17
    ௅
    2.17
    setzen
    2.17
     ſta
    2.16
     красивый
    2.13
    Activations Density 0.002%

    No Known Activations