© 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. 79350
    Prev
    Next
    INDEX
    Explanations

    citations or references

    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
    <sup>
    -0.92
     Er
    -0.78
     kiş
    -0.77
     Replacement
    -0.75
    <sub>
    -0.74
    茏
    -0.74
    rzysz
    -0.74
    Kafka
    -0.73
     för
    -0.72
     ${
    -0.71
    POSITIVE LOGITS
    citation
    1.32
    [
    1.02
     citation
    0.94
     citric
    0.87
    itando
    0.87
     clarification
    0.86
     clarifying
    0.84
    需要
    0.80
    StringLen
    0.80
    ][
    0.79
    Activations Density 0.018%

    No Known Activations