© 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. 28540
    Prev
    Next
    INDEX
    Explanations

    programming syntax and equations

    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
     after
    -0.91
    னு
    -0.84
     immediately
    -0.84
     continuing
    -0.83
    ندي
    -0.81
     idolatry
    -0.81
     télévis
    -0.78
     ПРО
    -0.77
    Rcpp
    -0.75
     diligent
    -0.74
    POSITIVE LOGITS
    similar
    1.10
    without
    1.07
    especially
    1.02
    particularly
    0.98
    mainly
    0.95
    elsif
    0.92
     mediocre
    0.92
    however
    0.92
    specifically
    0.92
     любые
    0.91
    Activations Density 0.028%

    No Known Activations