© 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. 120759
    Prev
    Next
    INDEX
    Explanations

    jumper cable or coaxial cable

    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
     effort
    -0.06
    という
    -0.06
    VO
    -0.06
     meinen
    -0.06
    Notwithstanding
    -0.06
    に取り組
    -0.06
     неви
    -0.06
     σχέ
    -0.06
     standardization
    -0.05
     creates
    -0.05
    POSITIVE LOGITS
     **,
    0.07
     Miller
    0.07
     actually
    0.07
     பயண
    0.06
    actually
    0.06
     しかし
    0.06
    eep
    0.06
     ale
    0.06
     Patrick
    0.06
    eud
    0.06
    Activations Density 0.001%

    No Known Activations