© 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. 97978
    Prev
    Next
    INDEX
    Explanations

    pursuant to

    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
    beitrag
    -0.91
    が使
    -0.87
    杀
    -0.81
     possiamo
    -0.79
    ífico
    -0.78
    büro
    -0.77
    ⌫
    -0.77
    尬
    -0.75
    ชาว
    -0.75
    вал
    -0.74
    POSITIVE LOGITS
     pursuant
    4.56
     Pursuant
    2.89
    Pur
    1.93
    pur
    1.91
     under
    1.86
     pursuance
    1.82
     pursu
    1.42
     pur
    1.38
     gemäß
    1.35
     согласно
    1.35
    Activations Density 0.092%

    No Known Activations