© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118690
    Prev
    Next
    INDEX
    Explanations

    following prepositions

    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
     entire
    -0.06
    ளே
    -0.05
     ही
    -0.05
     इंट्रा
    -0.05
     कंप्यूटर
    -0.05
    整个
    -0.05
     করতেই
    -0.05
    пор
    -0.05
     sklep
    -0.05
     大型
    -0.05
    POSITIVE LOGITS
     നമ്മുടെ
    0.07
     staffers
    0.06
     наших
    0.06
     идентифика
    0.06
     приорите
    0.06
     لدينا
    0.06
     שלנו
    0.06
     precursors
    0.06
     prioridad
    0.06
     naszego
    0.06
    Activations Density 0.025%

    No Known Activations