© 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. 120878
    Prev
    Next
    INDEX
    Explanations

    market value

    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
     maritime
    -0.08
     marit
    -0.06
     मौत
    -0.06
     wetensch
    -0.06
     יותר
    -0.06
     http
    -0.06
     ন্যাশনাল
    -0.06
     অনেকটাই
    -0.05
    “
    -0.05
     más
    -0.05
    POSITIVE LOGITS
     proyect
    0.07
     lemons
    0.06
    atilde
    0.06
     заболе
    0.06
    Trendy
    0.06
    持って
    0.06
     malfunctioning
    0.06
     terve
    0.06
     proximate
    0.06
     ठहर
    0.06
    Activations Density 0.007%

    No Known Activations