© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120350
    Prev
    Next
    INDEX
    Explanations

    charset=UTF-8

    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
    ');//
    -0.07
     tuna
    -0.07
    igram
    -0.07
     );//
    -0.07
    چے
    -0.06
     powerful
    -0.06
    raciones
    -0.06
    られて
    -0.06
    ভিয়েতনাম
    -0.06
    mails
    -0.06
    POSITIVE LOGITS
     either
    0.07
    land
    0.06
    .
    0.06
     O
    0.06
     Local
    0.06
    icity
    0.06
    ฤ
    0.06
     both
    0.06
     these
    0.05
    Local
    0.05
    Activations Density 0.002%

    No Known Activations