© 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. 120497
    Prev
    Next
    INDEX
    Explanations

    html tag attributes

    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
     pekerja
    -0.06
     হল
    -0.06
     casco
    -0.06
     just
    -0.06
     xmas
    -0.06
     basic
    -0.06
     시절
    -0.06
     namun
    -0.06
     rätt
    -0.06
     saturday
    -0.06
    POSITIVE LOGITS
     gunakan
    0.08
    stories
    0.07
     precedenti
    0.06
    🤷
    0.06
    所に
    0.06
     anteriores
    0.06
     stories
    0.06
     Stories
    0.06
    ऐसे
    0.06
     кандай
    0.06
    Activations Density 0.013%

    No Known Activations