© 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. 22-GEMMASCOPE-RES-131K
    4. 67191
    Prev
    Next
    INDEX
    Explanations

    contrast and consequence 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
     on
    -0.91
     sekä
    -0.88
    yn
    -0.86
     two
    -0.84
    intptr
    -0.81
     (
    -0.81
    seende
    -0.79
    figcaption
    -0.79
    glPopMatrix
    -0.78
     nữa
    -0.77
    POSITIVE LOGITS
     therefore
    1.67
    therefore
    1.45
     поэтому
    1.25
     Portanto
    1.23
    所以
    1.18
     rather
    1.17
     purpose
    1.14
    它的
    1.13
     objectives
    1.12
     portanto
    1.12
    Activations Density 0.065%

    No Known Activations