© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73002
    Prev
    Next
    INDEX
    Explanations

    separating clauses with conjunctions

    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_22/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
     rivi
    -1.04
     minera
    -0.99
     milieux
    -0.96
     meras
    -0.94
     haban
    -0.93
    歌詞
    -0.93
     Antara
    -0.91
    当社
    -0.91
     tenda
    -0.90
     Toscana
    -0.90
    POSITIVE LOGITS
     so
    1.51
     would
    1.50
     plus
    1.34
     too
    1.18
     Plus
    1.17
     unless
    1.17
    Además
    1.05
     поэтому
    1.05
     option
    1.05
    unless
    1.02
    Activations Density 0.048%

    No Known Activations