© 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. 109498
    Prev
    Next
    INDEX
    Explanations

    universal idioms and scales

    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
     邊
    -0.83
     turning
    -0.79
     plethora
    -0.78
     Nugent
    -0.77
    看護
    -0.76
    น์
    -0.75
    阀
    -0.75
     biggest
    -0.73
     squ
    -0.72
    בע
    -0.71
    POSITIVE LOGITS
    selbe
    0.94
    intem
    0.91
     CONCLUS
    0.90
     portefeuille
    0.89
    ترت
    0.88
    Significado
    0.86
     dourada
    0.85
    execSQL
    0.85
     Vorsitzende
    0.82
     quatrième
    0.81
    Activations Density 0.005%

    No Known Activations