© 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. 118190
    Prev
    Next
    INDEX
    Explanations

    distribution of licenses

    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
     их
    -0.07
     THEIR
    -0.06
    tmpobj
    -0.06
     αλλά
    -0.06
     uniquement
    -0.06
     इलाके
    -0.06
     أخ
    -0.06
     ambos
    -0.06
    }}+
    -0.06
     jų
    -0.06
    POSITIVE LOGITS
    四年
    0.06
     copyrights
    0.06
     upgrades
    0.06
    one
    0.06
     resourceful
    0.05
     partitions
    0.05
    ferm
    0.05
     வரலாற்று
    0.05
     नियामक
    0.05
    born
    0.05
    Activations Density 0.007%

    No Known Activations