© 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. 105051
    Prev
    Next
    INDEX
    Explanations

    alfa USSR Argon properties

    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
    ↵↵
    -3.81
     –
    -3.64
    ༀ
    -3.31
    *
    -2.97
    都是在
    -2.58
    “
    -2.53
     наша
    -2.42
         
    -2.36
     нам
    -2.31
                
    -2.27
    POSITIVE LOGITS
    鉆
    3.23
    蕷
    2.89
    ⡉
    2.72
    墻
    2.70
    輟
    2.66
     arbeta
    2.52
    不斷
    2.50
    熒
    2.47
    kipun
    2.45
    setViewName
    2.45
    Activations Density 0.019%

    No Known Activations