© 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. 120910
    Prev
    Next
    INDEX
    Explanations

    function $f:\mathbb R\to\mathbb R$

    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
     an
    -0.07
     इन
    -0.07
     our
    -0.07
     Ê
    -0.07
     these
    -0.07
     These
    -0.07
     successful
    -0.06
    These
    -0.06
     È
    -0.06
     the
    -0.06
    POSITIVE LOGITS
     garder
    0.07
     jokingly
    0.06
     पाण्याच्या
    0.06
    already
    0.06
     ponieważ
    0.06
     đã
    0.06
     eagerly
    0.06
    sometimes
    0.06
     sometimes
    0.05
     already
    0.05
    Activations Density 0.002%

    No Known Activations