© 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. 103769
    Prev
    Next
    INDEX
    Explanations

    code comments, purpose, and usage

    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
     purposes
    -1.12
     pur
    -0.98
     purpose
    -0.97
    Purpose
    -0.96
     PURPOSE
    -0.94
    PURPOSE
    -0.92
     purple
    -0.91
     Purdue
    -0.89
     pulse
    -0.88
     Purpose
    -0.85
    POSITIVE LOGITS
     .*
    0.87
    ⏺
    0.84
     denominada
    0.84
    ルの
    0.84
     nemlig
    0.80
    Inflater
    0.78
     seragam
    0.78
     בעל
    0.77
     leeftijd
    0.77
     dziennik
    0.77
    Activations Density 0.067%

    No Known Activations