© 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. 127905
    Prev
    Next
    INDEX
    Explanations

    definitions and technical terms

    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
     dobbiamo
    -0.06
     якщо
    -0.06
    zare
    -0.06
     우리는
    -0.06
    铖
    -0.06
    reason
    -0.06
    发生了
    -0.06
     माध्यम
    -0.06
     judgements
    -0.06
    扉
    -0.06
    POSITIVE LOGITS
     diferentes
    0.06
    Dictionary
    0.06
     быст
    0.06
     niewiel
    0.06
    最有
    0.05
     delivery
    0.05
     teknologi
    0.05
     evaluator
    0.05
     différente
    0.05
     несколь
    0.05
    Activations Density 0.001%

    No Known Activations