© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 32597
    Prev
    Next
    INDEX
    Explanations

    what causes specific outcomes

    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
    Negative Logits
     how
    -1.17
     either
    -1.13
    ParallelGroup
    -0.98
    carus
    -0.96
    either
    -0.96
    siah
    -0.95
    €™
    -0.94
     what
    -0.94
     nämlich
    -0.91
     방법
    -0.91
    POSITIVE LOGITS
     with
    1.20
     for
    1.08
     of
    1.05
     most
    1.05
     that
    1.02
     besonders
    0.99
     NOT
    0.99
     in
    0.93
     tidak
    0.91
     to
    0.90
    Activations Density 0.063%

    No Known Activations