© 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. 129112
    Prev
    Next
    INDEX
    Explanations

    city names after punctuation

    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
     bruise
    -0.06
    ')->
    -0.06
     determinant
    -0.06
    屓
    -0.06
    द्वितीय
    -0.06
    uei
    -0.05
     عرضه
    -0.05
     doe
    -0.05
    dic
    -0.05
    ned
    -0.05
    POSITIVE LOGITS
     além
    0.08
     además
    0.07
     this
    0.07
     oltre
    0.06
    以及
    0.06
     ਲਈ
    0.06
    为主
    0.06
     кроме
    0.06
     you
    0.06
    You
    0.06
    Activations Density 0.002%

    No Known Activations