© 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. 120786
    Prev
    Next
    INDEX
    Explanations

    sequential numbers

    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
    에서는
    -0.08
    では
    -0.06
     décoration
    -0.06
    রকম
    -0.06
    indications
    -0.05
     कार्
    -0.05
     पर्यंत
    -0.05
    Such
    -0.05
    iply
    -0.05
     Apparel
    -0.05
    POSITIVE LOGITS
     Это
    0.07
     complementar
    0.07
     consequently
    0.06
     on
    0.06
     dadurch
    0.06
     to
    0.06
    elson
    0.06
     unused
    0.06
     bacterial
    0.06
     onder
    0.06
    Activations Density 0.002%

    No Known Activations