© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131012
    Prev
    Next
    INDEX
    Explanations

    names, elections, and campaign materials

    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
    Hö
    -0.07
    しながら
    -0.06
    十分に
    -0.06
     ನಂತರ
    -0.06
     firmly
    -0.06
     aún
    -0.06
    还没
    -0.06
     poverty
    -0.06
     veröffent
    -0.06
    を使った
    -0.06
    POSITIVE LOGITS
     Ç
    0.05
    ALL
    0.05
    ̧
    0.05
    ▹
    0.05
     ሰዎች
    0.05
     supporters
    0.05
    Ç
    0.05
     nagyobb
    0.05
     захід
    0.05
    कांच्या
    0.05
    Activations Density 0.016%

    No Known Activations