© 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. 118962
    Prev
    Next
    INDEX
    Explanations

    Differential effect or amplification

    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
     demanda
    -0.06
     হয়তো
    -0.06
    使用
    -0.06
     Athenian
    -0.06
     derrière
    -0.06
     উদ্বোধন
    -0.06
     kullan
    -0.06
     use
    -0.06
     Prototype
    -0.05
     uży
    -0.05
    POSITIVE LOGITS
     jederzeit
    0.06
     committees
    0.06
     അദ്ദേഹം
    0.06
     dwie
    0.06
     Srbije
    0.06
     outils
    0.06
     karyawan
    0.06
    Commit
    0.06
     नये
    0.06
     তারা
    0.06
    Activations Density 0.003%

    No Known Activations