© 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. 48147
    Prev
    Next
    INDEX
    Explanations

    CSS properties or code assignments

    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
     maakt
    -1.04
    makeText
    -0.96
    .*;
    -0.94
    NELL
    -0.92
    ({
    -0.91
    LETON
    -0.90
     hice
    -0.90
    лно
    -0.88
    caped
    -0.88
    stair
    -0.87
    POSITIVE LOGITS
     stating
    1.06
     видеть
    0.95
    ,–
    0.94
    Privat
    0.93
     —,
    0.92
     particularly
    0.91
     at
    0.90
     principally
    0.88
     or
    0.88
     Bals
    0.88
    Activations Density 0.009%

    No Known Activations