© 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. 116085
    Prev
    Next
    INDEX
    Explanations

    in general

    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
    -0.07
     reimag
    -0.07
     recently
    -0.07
     précédemment
    -0.07
    However
    -0.07
     is
    -0.06
    ビジネス
    -0.06
    か
    -0.06
     Pren
    -0.06
     create
    -0.06
    POSITIVE LOGITS
    所有
    0.07
    所有的
    0.06
     所有
    0.06
     andar
    0.06
     and
    0.06
    which
    0.06
    整个
    0.06
     जिनको
    0.05
     monotonically
    0.05
    conditions
    0.05
    Activations Density 0.009%

    No Known Activations