© 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. 119106
    Prev
    Next
    INDEX
    Explanations

    choice or solution for need

    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
     soldadura
    -1.09
    必要があります
    -1.06
     empleos
    -1.02
     принимать
    -1.02
     manguera
    -1.00
     acoged
    -1.00
     and
    -0.96
     calefacción
    -0.96
    METHODOLOGY
    -0.94
     mediante
    -0.94
    POSITIVE LOGITS
     to
    3.11
     for
    2.75
     if
    1.98
     when
    1.72
     especially
    1.53
    Especially
    1.50
     anyone
    1.47
     because
    1.45
     choice
    1.36
     для
    1.35
    Activations Density 0.056%

    No Known Activations