© 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. 120272
    Prev
    Next
    INDEX
    Explanations

    counting items in groups

    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
     effectively
    -0.06
     工
    -0.06
    ienne
    -0.06
     সংসদে
    -0.06
     be
    -0.06
    มีความ
    -0.06
    ᒥ
    -0.06
     classy
    -0.06
    MainMenu
    -0.06
    まぁ
    -0.05
    POSITIVE LOGITS
     capitalismo
    0.07
     discussing
    0.06
     Discuss
    0.06
     обсужда
    0.06
    討論
    0.06
     primeras
    0.06
     discusión
    0.06
     primeiras
    0.06
     discussion
    0.06
     দিয়
    0.06
    Activations Density 0.004%

    No Known Activations