© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129683
    Prev
    Next
    INDEX
    Explanations

    mary and associated names

    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_22/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
     
    -3.33
    E
    -2.84
    ↵
    -2.80
     Also
    -2.38
    
    -2.31
    is
    -2.30
    だけでなく
    -2.30
     The
    -2.25
    ,"
    -2.23
     VERY
    -2.14
    POSITIVE LOGITS
    骘
    3.09
    卨
    3.05
    }
    2.83
     イラストレーション
    2.75
    ถ้า
    2.61
    ܆
    2.61
     現貨
    2.52
    鹟
    2.45
    鉝
    2.45
     书法
    2.36
    Activations Density 0.018%

    No Known Activations