© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120806
    Prev
    Next
    INDEX
    Explanations

    Heat stress references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propria
    -0.06
     evidente
    -0.06
     nella
    -0.06
     WHETHER
    -0.06
    Depending
    -0.06
     гораздо
    -0.06
     nahezu
    -0.06
    Horizontal
    -0.06
     completes
    -0.06
    种类
    -0.06
    POSITIVE LOGITS
     tiene
    0.06
     أن
    0.06
    他就
    0.06
     что
    0.06
     what
    0.06
    corresponding
    0.05
    ts
    0.05
    慧
    0.05
     هذ
    0.05
     researchers
    0.05
    Activations Density 0.001%

    No Known Activations