© 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. 119195
    Prev
    Next
    INDEX
    Explanations

    date and news labels

    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
    ড়ের
    -0.06
     Appet
    -0.06
     punishments
    -0.06
     किरणों
    -0.06
    它的
    -0.05
    हास
    -0.05
    アート
    -0.05
     इद
    -0.05
    それが
    -0.05
    リスト
    -0.05
    POSITIVE LOGITS
     synthèse
    0.06
    ിയ്
    0.06
     spokesperson
    0.06
     był
    0.06
    ?!?
    0.06
    ﹝
    0.06
    MO
    0.05
     বন্দরের
    0.05
    たちは
    0.05
     était
    0.05
    Activations Density 0.007%

    No Known Activations