© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130978
    Prev
    Next
    INDEX
    Explanations

    fault, grounding, insulation, current

    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
     InputListener
    -0.07
     registering
    -0.07
     verifying
    -0.07
     registro
    -0.06
     원하는
    -0.06
     certifying
    -0.06
     attest
    -0.06
     Stell
    -0.06
     ਸ
    -0.06
     handels
    -0.06
    POSITIVE LOGITS
     personale
    0.06
    him
    0.06
    Serious
    0.06
    ̉
    0.06
    ⑦
    0.06
    importance
    0.06
    ="/"
    0.06
    除了
    0.06
     transnational
    0.06
     allocated
    0.06
    Activations Density 0.016%

    No Known Activations