© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130247
    Prev
    Next
    INDEX
    Explanations

    suggested that give

    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
     cordova
    -0.06
     DUE
    -0.06
     وہاں
    -0.06
     FYI
    -0.06
     BTW
    -0.06
     વૈ
    -0.06
     IMO
    -0.05
     तुमच्या
    -0.05
    BTW
    -0.05
     klasik
    -0.05
    POSITIVE LOGITS
    ኵ
    0.07
     forty
    0.06
     four
    0.06
     jeżeli
    0.06
     모든
    0.06
    unches
    0.06
    quatre
    0.06
    所有的
    0.06
     fyra
    0.06
     ऐसा
    0.06
    Activations Density 0.035%

    No Known Activations