© 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. 34-GEMMASCOPE-RES-131K
    7. 82838
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and attributes

    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_34/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
    授權
    -1.00
    äuser
    -0.78
     willingly
    -0.77
    冠軍
    -0.76
     特徴
    -0.75
     comfortably
    -0.75
     調査
    -0.73
    འི་
    -0.70
    흥
    -0.70
    rowid
    -0.69
    POSITIVE LOGITS
     cs
    0.80
     nö
    0.79
    DOU
    0.77
    endesk
    0.76
     artwork
    0.75
     мен
    0.75
    ίκ
    0.74
     AVE
    0.74
    季度
    0.73
     صنایع
    0.72
    Activations Density 0.000%

    No Known Activations