© 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. 120593
    Prev
    Next
    INDEX
    Explanations

    prog_exists

    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
     to
    -0.08
     brother
    -0.07
    सबसे
    -0.06
     jaundice
    -0.06
     having
    -0.06
    мый
    -0.06
     generally
    -0.06
     الى
    -0.06
     finale
    -0.06
     mirroring
    -0.06
    POSITIVE LOGITS
     Ind
    0.06
     mỗi
    0.06
    intention
    0.06
     История
    0.06
     New
    0.06
     È
    0.06
    ántico
    0.06
     Historia
    0.06
     ประจํา
    0.06
     entre
    0.06
    Activations Density 0.002%

    No Known Activations