© 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. 34-GEMMASCOPE-RES-131K
    7. 45517
    Prev
    Next
    INDEX
    Explanations

    officially

    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
     Regardless
    -1.86
     regardless
    -1.85
     Despite
    -1.80
     Although
    -1.73
     despite
    -1.71
     Usually
    -1.69
     without
    -1.66
     While
    -1.64
     Almost
    -1.61
     although
    -1.55
    POSITIVE LOGITS
     verschillende
    1.94
     komplet
    1.68
     nowego
    1.67
    during
    1.57
     autén
    1.54
     relojes
    1.53
     différentes
    1.52
     ww
    1.50
     neón
    1.48
     salonu
    1.47
    Activations Density 0.046%

    No Known Activations