© 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. 115938
    Prev
    Next
    INDEX
    Explanations

    version, json, fonts, database

    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
    Negative Logits
     tome
    -0.06
     similar
    -0.06
     spesial
    -0.06
     स्कैन
    -0.06
     similaire
    -0.05
     ש
    -0.05
    Similar
    -0.05
     פ
    -0.05
     statue
    -0.05
    요
    -0.05
    POSITIVE LOGITS
     તથા
    0.06
     radically
    0.06
    tourism
    0.06
     наконец
    0.06
     rendez
    0.06
     employing
    0.06
     ceea
    0.06
     delectable
    0.06
     memakai
    0.06
     সর্বশেষ
    0.06
    Activations Density 0.005%

    No Known Activations