© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    scheduled events and proceedings

    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
     of
    -1.79
    :
    -1.55
     ‘‘
    -1.42
    ;
    -1.30
    </h1>
    -1.29
    .
    -1.27
     机械
    -1.26
    不但
    -1.23
    并不是
    -1.22
    鈣
    -1.21
    POSITIVE LOGITS
    ּוֹ
    1.58
    ִּ
    1.52
    problems
    1.46
     it
    1.45
    紲
    1.44
    韫
    1.43
    σθαι
    1.36
    ആ
    1.34
    atrième
    1.33
     الوزراء
    1.33
    Activations Density 0.150%

    No Known Activations