© 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. 11180
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
    ㄧ
    -1.34
     rocha
    -1.28
    欵
    -1.27
     concorda
    -1.25
     اکنون
    -1.24
     Flexib
    -1.23
     suporta
    -1.23
    一个小
    -1.23
     a
    -1.21
    瞜
    -1.20
    POSITIVE LOGITS
     красивые
    1.79
     också
    1.76
     niego
    1.61
     também
    1.59
    :"#
    1.56
     comienzos
    1.55
     всички
    1.55
     сча
    1.52
     también
    1.51
    enumerate
    1.50
    Activations Density 0.021%

    No Known Activations