© 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. 34-GEMMASCOPE-RES-131K
    7. 48687
    Prev
    Next
    INDEX
    Explanations

    mathematical `if` and `where` clauses

    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
    wnież
    -0.79
    ophone
    -0.78
    徜
    -0.76
     morfo
    -0.75
    mohan
    -0.75
     Augusta
    -0.75
     olimp
    -0.74
    ameters
    -0.74
    檻
    -0.74
    नों
    -0.73
    POSITIVE LOGITS
     where
    0.93
     if
    0.86
     for
    0.82
     when
    0.81
     whenever
    0.79
    niß
    0.79
    好在
    0.78
     hongos
    0.76
    Suerte
    0.76
    ⓘ
    0.75
    Activations Density 0.002%

    No Known Activations