© 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. 80983
    Prev
    Next
    INDEX
    Explanations

    words starting with "Ph"

    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
    Ngày
    -0.79
    Algo
    -0.78
     Xuân
    -0.71
    〉
    -0.71
    いただきたい
    -0.71
     puer
    -0.70
    NUMBER
    -0.70
     атмос
    -0.69
     Takeaway
    -0.69
     bé
    -0.68
    POSITIVE LOGITS
     Pha
    0.98
     illegitimate
    0.83
    dfn
    0.81
     ファ
    0.80
     Wheatley
    0.80
     Ph
    0.79
    kega
    0.76
    клон
    0.75
     pha
    0.75
     pH
    0.71
    Activations Density 0.027%

    No Known Activations