© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62608
    Prev
    Next
    INDEX
    Explanations

    code delimiters and null values

    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
    Negative Logits
     Schon
    -0.80
     Krim
    -0.79
     formando
    -0.78
     it
    -0.77
     Glaub
    -0.76
     empf
    -0.76
    jeron
    -0.76
     Auge
    -0.75
     Stande
    -0.75
     anytime
    -0.74
    POSITIVE LOGITS
     nullptr
    1.00
     nothing
    0.91
    Nothing
    0.89
     imposible
    0.87
     null
    0.86
    իմ
    0.86
     hôm
    0.86
     motoru
    0.84
     cero
    0.84
    örös
    0.83
    Activations Density 0.000%

    No Known Activations