© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75196
    Prev
    Next
    INDEX
    Explanations

    conditional and alternative logic

    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
    枉
    -0.84
    चाल
    -0.81
    swept
    -0.79
    ⦃
    -0.79
    を開催
    -0.78
    _{-\
    -0.78
     inggris
    -0.78
     bombe
    -0.77
     zó
    -0.77
    trainable
    -0.75
    POSITIVE LOGITS
     or
    1.09
     Alternatively
    0.96
     preferred
    0.95
     пър
    0.94
    Alternatively
    0.91
     hoặc
    0.89
     preferable
    0.85
     precedence
    0.80
    wyr
    0.79
    Then
    0.78
    Activations Density 0.035%

    No Known Activations