© 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. 20276
    Prev
    Next
    INDEX
    Explanations

    names ending in era

    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
     or
    -2.33
    或者
    -2.33
     которой
    -2.30
    鬭
    -2.27
     enormously
    -2.27
    我会
    -2.20
    I
    -2.20
    <bos>
    -2.17
     essenziale
    -2.17
     était
    -2.16
    POSITIVE LOGITS
     waren
    2.56
    不屑
    2.36
    .
    2.30
     пять
    2.27
    ፨
    2.22
     permitirá
    2.20
    0
    2.16
    
    2.09
    鍆
    2.06
    actéristi
    2.03
    Activations Density 0.027%

    No Known Activations