© 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. 97779
    Prev
    Next
    INDEX
    Explanations

    try again

    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
    TRY
    -1.02
     intentar
    -1.00
     帽
    -0.96
     try
    -0.96
     sóc
    -0.95
     tenemos
    -0.94
    璘
    -0.93
    Modul
    -0.92
     nevera
    -0.90
    řízen
    -0.90
    POSITIVE LOGITS
     to
    2.23
     with
    1.59
     again
    1.33
    other
    1.00
    Again
    0.96
    It
    0.93
     using
    0.93
     it
    0.90
    autres
    0.90
     accessing
    0.90
    Activations Density 0.060%

    No Known Activations