© 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. 129142
    Prev
    Next
    INDEX
    Explanations

    hexagonal lattices and networks

    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
    利き
    -0.07
     quotas
    -0.06
     increased
    -0.06
     reduced
    -0.06
    たん
    -0.06
     Gron
    -0.06
     restrictions
    -0.06
    ”…
    -0.06
     increases
    -0.06
     percentile
    -0.06
    POSITIVE LOGITS
    而被
    0.06
    新聞
    0.06
     причиной
    0.06
     Investig
    0.06
    तना
    0.06
     לד
    0.06
     दट
    0.05
     giver
    0.05
     میڈیا
    0.05
     Associ
    0.05
    Activations Density 0.003%

    No Known Activations