© 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. 128376
    Prev
    Next
    INDEX
    Explanations

    string literals

    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
     which
    -0.07
     also
    -0.06
     welche
    -0.06
     hvil
    -0.06
    ML
    -0.06
    isc
    -0.05
     fairly
    -0.05
    scheduling
    -0.05
    شكال
    -0.05
     effectively
    -0.05
    POSITIVE LOGITS
    KON
    0.07
    すべての
    0.07
     если
    0.06
    াদক
    0.06
     facteurs
    0.06
     Bi
    0.06
     Likewise
    0.06
     At
    0.06
     большинства
    0.06
    Nevertheless
    0.06
    Activations Density 0.003%

    No Known Activations