© 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. 90353
    Prev
    Next
    INDEX
    Explanations

    journeys and travel excursions

    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
    </sup>
    -1.55
    𝑒
    -1.48
     coloridas
    -1.42
    更好的
    -1.42
    (※
    -1.41
    т
    -1.41
    NegativeButton
    -1.35
    鱟
    -1.34
    蠱
    -1.30
     increase
    -1.30
    POSITIVE LOGITS
    旆
    1.85
     to
    1.84
    
    1.73
    ",
    1.71
    ጺ
    1.68
     trip
    1.65
    の絵
    1.63
    我最
    1.58
    тием
    1.55
     Of
    1.52
    Activations Density 0.019%

    No Known Activations