© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102863
    Prev
    Next
    INDEX
    Explanations

    words ending with ig

    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
     commonly
    -0.73
     Close
    -0.71
     strongly
    -0.71
     spec
    -0.71
     if
    -0.70
     should
    -0.70
    اق
    -0.70
    يرا
    -0.69
    ázky
    -0.69
     periodicals
    -0.69
    POSITIVE LOGITS
    gy
    0.96
    ificance
    0.94
     myriad
    0.90
     goofy
    0.86
    "],
    
    0.85
    гия
    0.85
     déclarations
    0.83
    ʻ
    0.83
    gles
    0.83
    gies
    0.81
    Activations Density 0.047%

    No Known Activations