© 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. 93499
    Prev
    Next
    INDEX
    Explanations

    compare or cf

    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
    ($)
    -0.94
     Чита
    -0.83
    costs
    -0.80
     espoir
    -0.78
    WillAppear
    -0.78
     appui
    -0.77
    Concurrency
    -0.76
     exklu
    -0.76
     pecho
    -0.75
     gjort
    -0.75
    POSITIVE LOGITS
     compare
    4.75
     cf
    4.59
     Compare
    4.03
    cf
    3.95
    compare
    3.86
    Compare
    3.67
     Cf
    3.34
    Cf
    2.98
     compares
    2.95
    COMPARE
    2.59
    Activations Density 0.019%

    No Known Activations