© 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. 129698
    Prev
    Next
    INDEX
    Explanations

    This neuron detects non-English "for" or "if" starters

    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
     but
    -0.09
    但
    -0.08
    不
    -0.08
    add
    -0.06
    用
    -0.06
    更是
    -0.06
    も含
    -0.06
    death
    -0.06
     但
    -0.06
    ということ
    -0.06
    POSITIVE LOGITS
     для
    0.08
     Если
    0.08
     für
    0.08
     Nếu
    0.07
     για
    0.07
     southeastern
    0.07
     eastern
    0.07
     برای
    0.07
     voor
    0.07
    सव
    0.06
    Activations Density 0.001%

    No Known Activations