© 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. 130244
    Prev
    Next
    INDEX
    Explanations

    item arrival or delivery

    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
    下的
    -1.45
     nhưng
    -1.44
    看
    -1.28
     một
    -1.26
    自己的
    -1.23
     CHtml
    -1.23
     他
    -1.20
    打算
    -1.20
    っぽい
    -1.20
     USING
    -1.18
    POSITIVE LOGITS
    nellement
    1.23
    =?,
    1.13
    𓇼
    1.11
    〰
    1.10
    我們的
    1.10
    Apre
    1.09
    不錯
    1.09
    詭
    1.08
     {},
    
    1.08
    <0xE1>
    1.08
    Activations Density 0.027%

    No Known Activations