© 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. 116848
    Prev
    Next
    INDEX
    Explanations

    solid state electrolytes conductors

    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
     очи
    -0.07
     black
    -0.06
     Arche
    -0.06
    டுகளை
    -0.06
     Black
    -0.05
     electrónico
    -0.05
     pyrolysis
    -0.05
     sets
    -0.05
     sáng
    -0.05
    omethyl
    -0.05
    POSITIVE LOGITS
     promote
    0.06
    行走
    0.06
     쭉
    0.06
     require
    0.06
     जलदाय
    0.06
    Require
    0.06
     immig
    0.06
     missionary
    0.06
     χρόνια
    0.06
     nomadic
    0.06
    Activations Density 0.004%

    No Known Activations